AstroWay Core astrology

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint, idempotentHint. Description adds that it returns a 'plain-text human-readable summary' and clarifies the budget-checking purpose, providing useful context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three efficient sentences: purpose, usage guidance, and return format. Front-loaded with key information, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite lacking an output schema, the description specifies the return format (plain-text human-readable summary). For a simple status check tool, this is complete and sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has zero parameters, so schema coverage is 100%. Description does not need to explain parameters, and it adds value by hinting at the output format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'Check' and the resource 'API key status' with specific attributes (tier, credit balance, rate limits, monthly cycle reset). It distinguishes itself from the many sibling astrology calculation tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to run this tool BEFORE invoking expensive endpoints, providing credit thresholds (Tier 4+ at 100+ credits, Tier 6/7 at 500-5000 credits) to confirm budget.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuine behavioral context beyond them: executors are kept out of the vendor objects because an unexpected key causes a 400 on the vendor side, and cost is flagged as not in the public credit manifest. That is real operational value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly three sentences, front-loaded with the purpose before the format and executor caveats. It is dense but each sentence carries information, though the format explanation partially duplicates the schema's own enum description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full annotation coverage, the description need not explain return values, and it appropriately focuses on the vendor-shape contract and the executors/400 gotcha. It is nearly complete, with the only gap being sibling disambiguation rather than missing operational detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter in depth (limit ceiling rationale, select values, precision semantics). The description only restates format and its default, adding no parameter meaning the schema lacks. Baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool returns: tool definitions for an agent framework, generated from the live OpenAPI document. It is specific about the resource and the vendor-shape variants (openai vs anthropic objects). However, it never distinguishes this from the near-identical sibling astroway_mcp_tools_list, which an agent would plausibly confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use, when-not-to-use, or alternative-naming guidance. The mention that openai objects 'spread straight into a chat completion' implies a use case, but the agent is left to infer when this endpoint is preferable to astroway_mcp_tools_list or the MCP tool-call streaming siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-annotation context: the POST endpoint and the '[Cost: 20 credits (Tier 2)]' pricing, which is useful for budget-aware planning. It says nothing about auth or result payload, but the output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The one-sentence purpose is front-loaded and the bracketed metadata lines are scannable and compact. The endpoint line is close to redundant given the tool-name-to-route mapping, but nothing is bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output values need not be described because an output schema exists, and annotations cover safety. However, for a 15-parameter natal-chart calculation, the description never explains how the natal reference is supplied or what the defaults (tropical vs sidereal, house system) mean, leaving a meaningful gap against the 33% parameter coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (fields, ayanamsa, timezone, precision, timezoneOffset are documented; zodiacType, houseSystem, cosmogram, ayanamsaId, city, name, date, time, latitude, longitude are not). At this low coverage the description is expected to compensate, yet it only repeats the four required parameter names, adding no meaning beyond the schema's own required array.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Calculate) and resource (antiscia and contra-antiscia) and even defines the technique parenthetically as mirror points along the Cancer/Capricorn axis, which conceptually separates it from neighbours like midpoints or parallel_aspects. It does not name an alternative sibling explicitly, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no comparison to sibling techniques such as astroway_aspects_midpoints or astroway_aspects_parallel_aspects. The only contextual aid is the bracketed '[Required: date, time, latitude, longitude]', which restates the schema's required list rather than telling the agent when this tool is the right choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description adds the credit cost (20 credits, Tier 2) and the endpoint, which is useful operational context, but nothing about latency, auth, or the difference between built-in and custom lots.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences front-load the purpose and the return content, followed by compact bracketed metadata for group, endpoint, and cost. No wasted prose, though the metadata lines are boilerplate rather than descriptive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the 100%-covered input schema handles all parameter detail. Annotations carry the safety profile, so the remaining gap is only the lack of alternative-tool routing, which is minor for a single-purpose calculation endpoint.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the body, fields, and precision parameters are already fully documented in the schema. The phrase 'and any custom formula' loosely gestures at the parts array, but adds no syntax or constraint detail beyond what the schema already provides; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Calculate) and resource (Arabic parts / Lots) and the input context (a natal chart), plus what is returned (positions for standard lots such as Fortune and Spirit). It is clearly distinct from the many rendering/calendar siblings, though it never explicitly contrasts itself with any of them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites beyond 'from a natal chart', and no naming of alternatives or when this should be preferred over other points/aspects tools. Usage must be inferred entirely from the tool name and group tag.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the full safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine context beyond them: cost (10 credits, Tier 1), endpoint (POST /v1/aspect-bar), and the semantic output behavior (bars span the orb duration, exact dates marked). It does not cover auth requirements or pagination/response-size limits for a date-range query.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core transformation in the first sentence, followed by a compact metadata block for group, endpoint, required params, and cost. Efficient and scannable, with no redundant prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and annotations cover the safety profile. However, with 10 parameters at 20% schema coverage, six tuning parameters (maxOrb, stepDays, aspectAngles, the planet/visibility ID lists) are unexplained in both places, leaving the definition incomplete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20%, so the description carries compensation duty, yet it explains nothing about maxOrb, stepDays, planet1Ids/planet2Ids, aspectAngles, or visiblePlanetIds — the parameters that actually shape the result. It confirms startDate/endDate as required, which the schema already states, adding little.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Transform aspect timelines into Gantt-style bars grouped by transit planet') and clarifies the output shape (duration in orb, exact dates marked). It clearly conveys this is a visualization/transformation tool rather than raw data, distinguishing it from data-returning siblings, though it never names astroway_aspects_aspect_timeline or astroway_render_timeline as relatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Useful for visual transit calendars' implies the intended use case but gives no explicit when-to-use, when-not, or alternatives. An agent must infer when to prefer this Gantt-bar form over the aspect timeline or render_timeline sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds that the output includes enter/exact/leave dates, which is meaningful behavioral context beyond the annotations. It does not disclose cost or performance limits, but the annotations carry the main safety burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and efficient, with no wasted words. The bracketed metadata lines (Group, Endpoint, Required, Cost) are structured but slightly break the flow, though they add useful routing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter tool with only 22% schema description coverage, the description is too thin. It never clarifies default behavior for maxOrb, stepDays, or aspectAngles, nor how the enter/exact/leave dates are formatted. It also omits any mention of pagination or output shape despite having an output schema, which helps but doesn't fully bridge the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 22%, and the description does not compensate by explaining the semantics of maxOrb, stepDays, aspectAngles, planet1Ids, or planet2Ids. It mentions 'two specific planets,' hinting at the duality of planet arrays, but leaves the orb, step, and aspect-angle parameters completely undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Calculate a timeline of when two specific planets form an exact aspect within a date range.' This clearly distinguishes it from siblings like astroway_calendar_aspects (a broader calendar) and astroway_aspects_aspect_bar. It could more explicitly differentiate from those siblings, but the core purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage via 'within a date range' and 'two specific planets,' but never states when to choose this tool over siblings like astroway_calendar_aspects or astroway_aspects_aspect_bar. No explicit when-not or alternatives are provided, so the agent must infer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value: star count, orb default and hard cap, closest-first ordering, and the 20-credit Tier 2 cost — details not present in the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence front-loads the output content and scope, followed by compact bracketed metadata lines. No sentence is filler; defaults and limits are packed into the lead sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-shape explanation is unnecessary, and cost/required fields are disclosed. The main gap is the unexplained relationship to the fixed-star catalog sibling and the mention of `stars`/`orb` inputs that the schema does not expose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% across 15 parameters, so the description should compensate more than it does. It does explain `stars` and `orb` semantics (default 1, max 5), but neither appears in the input schema, and parameters like zodiacType, houseSystem, cosmogram, city, and name are left to the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource — fixed-star positions at the birth moment plus conjunctions with natal planets, with defaults (36 classic stars, orb 1°, capped at 5°) and sort order (closest first). This clearly separates it from the many aspect/point siblings, though it does not explicitly name `astroway_aspects_fixed_stars_catalog` as the alternate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The bracketed metadata (group, endpoint, required fields, credit cost) gives useful context, but there is no explicit statement of when to use this versus the fixed-star catalog or other aspect tools. Usage is only implied by the group label 'Aspects & Points'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the data is static, drawn from fixstars.cat, the 36-star astrological default set is flagged in the output, and it costs 5 credits. That is meaningful disclosure beyond the structured fields, though it omits response shape or pagination details (partly covered by the output schema).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense, front-loaded sentence plus three bracketed metadata lines (group, endpoint, cost) that all carry actionable information for the agent. No filler; slightly heavy packing of five output fields into a single clause, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be re-explained, yet the description still enumerates the catalog columns. Combined with the cost, endpoint, and 'no chart needed' note, an agent has everything required to select and invoke this reference tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the two declared parameters (fields, precision), so the schema does the heavy lifting and baseline is 3. Notably the description introduces an '?maxMagnitude=' trim option that does not appear in the input schema, which adds information but also creates ambiguity about whether it can be passed as a tool argument or only as a raw query string.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete resource and scope: the star names the API accepts, sourced from Swiss Ephemeris fixstars.cat, with the exact fields returned (traditional name, Bayer nomenclature, constellation, magnitude, default-set flag). It also implicitly separates itself from the chart-based sibling astroway_aspects_fixed_stars via 'Static lookup, no chart needed', though it never names that sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'Static lookup, no chart needed' tells the agent this is a prerequisite/reference call rather than a computation, and the maxMagnitude note signals a filtering option. There is no explicit statement of when to call this versus astroway_aspects_fixed_stars or astroway_geo_parans_star, so the agent must infer the routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as a read-only, idempotent, non-destructive, closed-world operation, so safety is covered. The description adds genuinely useful non-annotation context: the endpoint, the credit cost (20 credits, Tier 2), and which fields are mandatory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose sentence is front-loaded and complete, followed by a compact bracketed metadata block (group, endpoint, required fields, cost). No sentence is wasteful and every line carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a 15-parameter calculation tool whose optional configuration meaningfully alters the result, the description is silent on those choices, leaving a real gap that the schema only partly fills.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, so the description must compensate for eleven undocumented optional parameters. Instead it merely restates the four required fields already declared in the schema's required array, adding essentially no semantic value for options like ayanamsa, zodiacType, houseSystem, or timezone handling.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Calculate') and resource ('Gauquelin sector positions (1–36)') with scope ('for all planets') and an outcome qualifier ('indicating whether each planet is in a power zone'). This is a distinct astrological technique with no competing sibling, so an agent can identify it immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lists required inputs and cost but gives no when-to-use guidance, no exclusions, and never names an alternative sibling. An agent must infer entirely from the name when this technique applies rather than, say, midpoint or parans tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered externally. The description adds real value beyond annotations by disclosing cost (20 credits, Tier 2), the endpoint, and required inputs. It stops short of noting response size or how the optional aspect inclusion is toggled, so a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose in the first sentence, followed by a short optional extension, then a compact bracketed metadata block. No filler sentences. The metadata block is dense but scannable and each line carries operational value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose, and annotations cover safety. But for a 15-parameter tool with only 33% schema coverage, the description leaves substantial gaps around which parameters enable sidereal mode, house system choice, and the compact-mode fields/precision options. It is minimally viable rather than complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% across 15 parameters, so the description is expected to compensate and does not. It restates the four required inputs and vaguely alludes to an optional aspect toggle without naming the controlling parameter. Key knobs such as zodiacType, houseSystem, ayanamsaId, precision, and cosmogram receive no explanation in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Calculate all planetary midpoints and their zodiac positions,' with an optional aspect extension. An agent can tell it computes midpoints rather than, say, midpoint trees or antiscia. However, it offers no explicit contrast with the close sibling astroway_aspects_midpoint_trees, so differentiation relies on the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives like astroway_aspects_midpoint_trees or astroway_aspects_aspect_bar. The only contextual markers are the required-inputs and cost lines, which inform feasibility rather than selection. The agent must infer the use case entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds genuinely useful operational context (endpoint, Tier 2 cost of 20 credits) not present in annotations, but says nothing about output shape or what a 'midpoint tree' actually resolves to.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action in the first clause, followed by compact structured metadata lines. Nothing is padded, though the group/endpoint/cost footer is boilerplate rather than task-relevant prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. Annotations cover the safety profile. However, for a domain-specific Uranian technique whose sibling tool (astroway_aspects_midpoints) is nearly identical, the description leaves the agent without enough to know when this tool is the right pick.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents the body, orb, fields and precision parameters. The description's mention of 'within a given orb' loosely points at the orb parameter but adds no syntax, defaults, or range detail beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Calculate') and a well-scoped resource ('Uranian midpoint trees and planetary pictures (symmetries) for each focal planet within a given orb'). This is more than a restated name, but it does not distinguish itself from the very close sibling astroway_aspects_midpoints, so the agent cannot route between them from the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no named alternative, despite a near-identical sibling (astroway_aspects_midpoints) that would be the natural confusion point. The only usage context provided is a group/endpoint/cost footer, which is operational metadata rather than selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new operational context (POST endpoint, 20-credit Tier 2 cost) but says nothing about return structure, orb defaults, or computation edge cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence states the operation and defines both aspect types; the metadata block is terse and structured. No wasted prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a stateless calculation tool with a complete input schema, a published output schema, and full annotation coverage, the description supplies what the structured fields do not: cost and endpoint. The main remaining gap is the absence of any routing hint among the many sibling aspect tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents date, time, latitude, longitude, orb, fields, and precision in detail. The phrase 'within orb' signals the orb parameter's role but adds no syntax, default, or range information beyond what the schema provides. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('calculate parallel and contra-parallel aspects between all planets within orb') and defines both terms inline, so the agent knows exactly what computation is performed. It does not explicitly differentiate itself from sibling aspect tools such as antiscia or midpoints, but the named resource ('parallel aspects') is distinctive enough to route correctly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, or alternative guidance is given; the only added context is grouping, endpoint, and cost. The agent is left to infer that this is the declination-aspect tool versus other aspect families based solely on the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful billing context ('10 credits, Tier 1') and the required parameter, but does not disclose rate limits, auth needs, or other behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence front-loads the core purpose, and the bracketed metadata is compact and structured. Every line earns its place without waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple lookup with an output schema and full safety annotations, the description covers the required input and cost. It is complete enough to call correctly, though usage routing remains absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, with 'longitudes' lacking a schema description. The description compensates somewhat by calling them 'ecliptic longitude' and marking the parameter required, but it adds no meaning for the compact-mode 'fields' and 'precision' parameters beyond what the schema already documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Return') and resource ('Sabian symbol') and scopes it to 'each given ecliptic longitude' with the Dane Rudhyar attribution. It is clear, but it does not name or distinguish itself from any sibling aspect tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives. The required-parameter and cost notes are operational, not usage context, and no sibling tool is referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful operational context the annotations lack — the endpoint (POST /v1/algol-minimum) and the cost (10 credits, Tier 1) — but says nothing about the response or any computation caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and free of padding, and the bracketed metadata block (group, endpoint, required params, cost) is compact and scannable. Slightly over-formatted for the amount of substantive content, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the endpoint/cost block is a plus. Still missing are sibling disambiguation against algol_minimum_nearest and any explanation of the longitude parameter, both of which an agent needs to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40%: startDate and endDate carry no descriptions beyond a date regex, and the longitude parameter is completely undocumented in both schema and description — its role in an Algol-minimum calculation is unexplained. The description only restates that startDate and endDate are required and adds no format or semantic detail, so it fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource — finding the nearest minimum-brightness moment of Algol within a date range — and even identifies the star (Beta Persei, an eclipsing variable). However, it does not differentiate itself from the close sibling astroway_calendar_algol_minimum_nearest, which an agent could easily confuse with this tool given the near-identical name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, or prerequisite guidance is provided. The obvious alternative, astroway_calendar_algol_minimum_nearest, is never mentioned, leaving the agent to guess which of the two Algol tools matches its intent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it is a POST endpoint, requires a date, and costs 10 credits (Tier 1). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence followed by a compact metadata block. Every element earns its place and there is no wasted prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and annotations cover safety. The description supplies endpoint, cost, and required parameter, but does not clarify sibling alternatives or provide additional parameter semantics for the undocumented inputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 50%, and the description only notes that date is required, which is already in the schema. It does not explain the longitude parameter, nor does it add meaning beyond the schema for fields, precision, or the date format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: find the single nearest Algol brightness minimum relative to a date. The purpose is clear, but it does not differentiate itself from the sibling astroway_calendar_algol_minimum, which likely lists minima rather than finding the nearest one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it: when you need the nearest Algol minimum around a given date. It provides no explicit when-not guidance or alternatives, and does not mention the related sibling tool for listing minima.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real context: the return shape, the per-pair astro.com orb matrix methodology, the fact that it shares calcAspects() with the chart endpoint, and an explicit cost of 10 credits (Tier 1), which is not derivable from the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the first gives the output contract and methodology, the second the differentiating trade-off. The bracketed group/endpoint/required/cost block is scannable metadata with no filler, and the most important content (what it returns, why it differs) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose, and the annotations cover the safety profile; the description also supplies endpoint, required params and cost. However, for a 15-parameter tool with only 33% schema coverage, the description does not close the gap on the ~10 undocumented inputs, leaving an agent reliant on inference for options like houseSystem and zodiacType.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% across 15 parameters, so the description carries a compensation burden it does not meet. It merely restates the four required params (date, time, latitude, longitude) already marked required in the schema and adds nothing about undocumented fields such as zodiacType, houseSystem, cosmogram, name, or city, nor does it explain the compact-mode interaction of fields/precision.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('standalone aspect calculation: full inter-planetary aspect list') and names the exact returned fields (type / exactAngle / orb / isApplying). It also carves itself out from the general chart endpoint ('same calcAspects() as /chart but without planet positions / houses / midpoints overhead'), though it does not distinguish itself from the many other aspect siblings such as parallel_aspects or moon_aspects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'standalone ... without planet positions / houses / midpoints overhead' implies a when-to-use case (call this when you only need aspects, not a full chart), but there is no explicit statement of when to prefer this over siblings like astroway_calendar_moon_aspects or astroway_aspects_parallel_aspects. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds materially useful operational context beyond that: endpoint, cost of 100 credits at Tier 4, and required fields. It still says nothing about output granularity (e.g. per-year vs per-day index values), which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One tight definitional sentence followed by bracketed metadata lines (group, endpoint, required, cost). Front-loaded and largely free of filler, though the metadata block partially duplicates the schema's required list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, and annotations carry the safety profile. However, for a 5-parameter tool with a 40% schema coverage, the unexplained 'pairs' argument and the undefined semantics of the year range leave real gaps for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40%. startYear and endYear are bare number/null with no schema description, and the description only restates them as required without explaining units, inclusivity, or valid range. The 'pairs' parameter is completely undocumented in both schema and description, so the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Calculate), a named resource (André Barbault Cyclic Index), defines it (sum of all outer planet separations), and gives its interpretive purpose (global crisis periods). This is distinguishable from the many sibling cycle/phase tools without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'to indicate global crisis periods' implies why an agent would call it, but there is no explicit when-to-use, no condition selecting it over astroway_calendar_planetary_cycles or astroway_calendar_planetary_phases, and no exclusions. Usage is inferable but not guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds useful operational context — the POST endpoint, that 'year' is required, and a cost of 100 credits (Tier 4) — but discloses no additional behavioral traits beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two front-loaded sentences state purpose and return contents, followed by a compact bracketed metadata block for group, endpoint, required param, and cost. Little waste, though the return-content sentence is partly redundant given an output schema exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple lookup tool, the description covers endpoint, required parameter, cost tier, and output fields, with annotations carrying the safety profile and an output schema handling return structure. The main gap is the unexplained interaction between the 'year' and 'yearsRange' parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%: the schema documents 'fields' and 'precision', but 'year' and 'yearsRange' are bare. The description's phrase 'year or multi-year range' hints at the year/yearsRange distinction but does not explain when one supersedes the other, so it only partially compensates for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find solar and lunar eclipses') plus scope ('within a given year or multi-year range'), and the response contents ('type, date, and geographic visibility data'). It is clear what the tool does, though it does not differentiate itself from the nearby sibling astroway_geo_eclipse_analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions that eclipses can be found in 'a given year or multi-year range' but never states when to use this tool versus alternatives such as astroway_geo_eclipse_analysis or astroway_render_eclipse_path, and gives no exclusions or prerequisites. Usage must be entirely inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: the auto-fallback behavior for quadrant systems above 66.5° latitude, plus cost (10 credits) and endpoint. It does not discuss precision/rounding behavior or any rate limits, but the fallback disclosure is meaningful value-add.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and outputs, followed by supported systems and the fallback caveat. The bracketed metadata block (group, endpoint, required, cost) is compact and scannable. Nothing is wasted, though the supported-systems list drifts slightly toward an unstructured enumeration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and the annotations cover the safety profile. However, for a 15-parameter tool with only 33% schema coverage, the agent is left guessing at several optional inputs (cosmogram, zodiacType, precision, fields). Adequate at the surface level but incomplete on configuration.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, so the description should compensate, and it largely does not. It names house systems in prose (Placidus, Koch, Campanus...) which partly decodes the opaque houseSystem letter enum, but several parameters (city, name, cosmogram, zodiacType, ayanamsaId) remain undocumented in both places. Required inputs are listed, matching the schema, adding no new semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Standalone house calculation') and enumerates exactly what is produced (12 cusps + ascendant + MC + ARMC + vertex + co-asc + polar-asc), which is far more specific than the title 'House Cusps'. 'Standalone' implicitly separates it from full-chart siblings like astroway_western_chart, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is only implied by the word 'Standalone' — there is no explicit 'use this when you need only houses, use western_chart when you need planets too' routing. The one genuine usage caveat given is the auto-fallback warning at |lat|>66.5°, which tells the agent when results may degrade, but when-to-use vs alternatives is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description nonetheless adds real behavioral context beyond them: retrograde re-entries are included in results and the call costs 100 credits (Tier 4), which is a material resource constraint an agent should weigh.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose sentence is front-loaded and wastes nothing, and the bracketed metadata block (group, endpoint, required, cost) is scannable. Minor redundancy in re-listing required parameters that the schema already declares.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description supplies purpose, required inputs, endpoint and cost. The remaining gaps are sibling differentiation and planetId/date semantics, which are minor for a read-only lookup tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40%: planetId, startDate and endDate carry no descriptions, while fields and precision are documented in the schema. The description's '[Required: planetId, startDate, endDate]' merely restates the schema's required array and adds no format or semantic detail (e.g. planetId encoding), so it does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find all sign ingresses for a planet') with a scoping qualifier ('within a date range') and clarifies that retrograde re-entries are included. This is clear and distinguishable from the calendar family at a glance, though it never names a sibling (e.g. retrograde_periods) to sharpen the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the planet + date-range framing, so an agent can infer when the tool applies. However, there is no explicit when-to-use/when-not guidance and no routing to alternatives such as astroway_calendar_retrograde_periods or astroway_calendar_planetary_cycles, which are the closest overlapping siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered by structured data. The description's only genuinely additive behavioral fact is the cost (100 credits, Tier 4), which is useful for budget-aware planning but is metadata rather than behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose sentence, then a compact bracketed metadata block for group, endpoint, required params and cost. Efficient and scannable, though the endpoint and group lines add little for an agent selecting a tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no elaboration, and the description still names the four data categories the agent gets back. For a 6-parameter read tool with full annotation coverage, this is nearly complete; only the relationship to overlapping sibling tools is left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%, with fields, precision, timezone and timezoneOffset well documented in the schema itself; only year/month lack descriptions, and the description merely repeats that they are required. No additional parameter meaning (formats, ranges, default timezone behavior) is contributed beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Calculate a lunar calendar for a given month') and enumerates the four output categories, which is more than a restatement of the title. It does not, however, distinguish itself from narrow siblings such as astroway_calendar_moon_phase or astroway_calendar_moon_voc, which cover single slices of this same data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the monthly scope and the enumeration of events, but there is no explicit when-to-use guidance and no routing to the cheaper single-purpose siblings (moon_phase, moon_voc, ingresses) that an agent might prefer. The 'Required: year, month' line states inputs, not usage conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description is not required to restate it. What it adds beyond structured data is modest: the applying/separating nature of the results and the cost tier (100 credits, Tier 4), which is genuinely decision-relevant for an agent budgeting calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence states purpose and use case, followed by compact bracketed metadata lines (group, endpoint, required params, cost) that are easy to scan. Nothing is padded, though the metadata block consumes space without adding semantic content to the core sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and annotations cover safety and idempotency; the description supplies purpose, required inputs, use domain and cost. The remaining gap is inter-sibling routing against astroway_calendar_aspects, which an agent would have to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: fields and precision are documented in the schema, while year and month are only bounded integers. The description's "within a date range" plus the [Required: year, month] line confirms the two period parameters, but adds no meaning (e.g. whether month alone defaults to full-month granularity) beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — aspects the Moon makes within a date range — and adds the applying/separating detail, so the agent knows exactly what is computed. It does not, however, differentiate itself from the nearby astroway_calendar_aspects sibling (all bodies) or from the other Moon tools (moon_phase, moon_voc).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"useful for electional and horary work" gives a use-case context, which is more than nothing, but it never says when to prefer this over astroway_calendar_aspects or the other Moon-calendar tools, and gives no exclusions or prerequisites. Usage is implied rather than directed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly/idempotent/non-destructive, so the description is not required to restate safety. It adds genuinely new behavioral context: the credit cost and tier, the POST endpoint, the geocentric reference frame, and the specific ephemeris method (Meeus Ch.48). The word 'Current' is slightly imprecise next to the required date/time, but 'at a given moment' immediately corrects it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short lines, front-loaded with the purpose and outputs before the grouped metadata (group, endpoint, required, cost). Every line carries information; there is no filler or restated verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value documentation is not needed, and the annotations carry the safety profile. What is missing is guidance for a 15-parameter request: no note on which optional parameters meaningfully affect a moon-phase result, no mention of timezone/timezoneOffset interaction for a location-based calculation (though the schema itself covers that well), and no differentiation from the render sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only 33% of the 15 parameters carry schema descriptions, so the description must compensate and largely does not. Its single parameter line merely restates the four required fields already declared in the schema's 'required' array, and adds no meaning for undocumented parameters such as city, name, cosmogram, zodiacType, houseSystem, or ayanamsaId — several of which look only tangentially relevant to a moon-phase calculation and would benefit from explanation or a usage note.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific computed resource (moon phase) and enumerates its outputs: illumination %, age in days, elongation, waxing/waning, and sun/moon zodiac signs, plus the computational basis (Meeus Ch.48, geocentric Sun-Moon elongation). An agent can tell exactly what this returns. It does not, however, name or differentiate itself from the close sibling astroway_render_moon_phase or astroway_calendar_lunar_calendar, which likely overlap in subject matter.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the output list and the '[Required: date, time, latitude, longitude]' line, but there is no explicit when-to-use statement, no exclusion, and no routing to alternatives such as the render or lunar-calendar siblings. The '[Cost: 10 credits (Tier 1)]' line gives useful context for choosing among tools but is not a usage rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, non-destructive, idempotent) and the description correctly doesn't contradict them. It adds the useful domain rule for what a VOC period is, but with 7 parameters (rangeDays, timezone, precision, fields, timezoneOffset) the description says nothing about range limits, timezone handling, or compact mode — leaving that entirely to schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences with the definition front-loaded and no wasted words. Metadata block (group/endpoint/required/cost) is boilerplate but useful for routing. Could be marginally improved only by naming a sibling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, 10-credit query returning a range of periods, the description omits how far it can span, that rangeDays controls the window, and how timezone affects output. An output schema exists, so return format needn't be described, but the usage constraints (range limits, credit cost already noted) are only partially covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 57%, so the schema documents timezone, timezoneOffset, precision, and fields but leaves rangeDays (and both required date/time) undescribed. The description adds no parameter meaning at all, and doesn't compensate for the rangeDays gap. Baseline 3 is appropriate for this coverage level.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Find) and resource (Moon void-of-course periods) plus the defining rule 'from last aspect until entry into the next sign.' Clear and distinguishable from siblings like astroway_calendar_moon_aspects, but doesn't explicitly name which sibling differs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no alternatives named, no exclusions. The agent must infer the tool's place among the many calendar_* siblings entirely on its own.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered structurally. The description's genuine addition is the cost disclosure ('100 credits, Tier 4') and the endpoint, which help an agent reason about budget. It adds nothing about output granularity or volume of matches, so a 3 is warranted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and the bracketed metadata block is compact and scannable. Every line earns its place, with no redundancy or filler to trim.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be described, and annotations carry the safety profile. The description supplies endpoint, required params, and cost, which is sufficient for an agent to invoke it correctly. Only the distinction from sibling cycle tools is unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (fields and precision are documented there, the four required ids/dates are not). The description compensates partly by naming the four required parameters and framing planet1Id/planet2Id as a conjunction pair, but adds no value for the undocumented precision/fields semantics, which the schema handles itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find all conjunctions between two planets within a date range') and adds the domain outcome ('defining the start of a new synodic cycle'). This is clear and self-contained, but it does not differentiate itself from close siblings like astroway_calendar_cyclic_index or astroway_calendar_planetary_phases, so the agent can't tell them apart from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no named alternative. The metadata lists required parameters and a cost tier, but never says when this tool is preferred over the related cyclic_index or aspects calendar tools. Usage must be inferred entirely from the purpose sentence.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, closed-world, and non-destructive traits, so the bar is lower. The description still adds real context: the caching rationale for omitting isCurrent, and the precise 'not false, it is unasked' semantics, which the agent could not infer from annotations alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and the hour-count rule are front-loaded, and the atLocalHour rationale follows economically. The metadata block (group, endpoint, required, cost) is boilerplate but compact; there is no rambling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't document return values, and it correctly names startHour/endHour/isCurrent. Combined with annotations and the schema's timezone/timezoneOffset docs, an agent has enough to call this correctly, though no cross-tool routing is offered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 63%, with strong per-parameter docs for timezone, timezoneOffset, precision, and atLocalHour. The description largely restates the atLocalHour schema text and only adds the output-side names startHour/endHour, so it meets but does not exceed the baseline for partially documented params.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource and computation: Chaldean planetary hours for a date and place, with the defining rule that hours are 12 sunrise-to-sunset and 12 sunset-to-sunrise and are rarely 60 minutes. That framing clearly separates it from siblings like planetary_phases and planetary_cycles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear conditional guidance for atLocalHour (send it to get isCurrent, omit it for cacheable results), but never says when to choose this tool over siblings such as sun_times or lunar_calendar. Usage is implied by the topic rather than explicitly routed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful context beyond them: the endpoint, the four required inputs, and a 20-credit Tier 2 cost, which is a real operational constraint an agent should weigh before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and dense with useful detail, and the bracketed metadata block is scannable. The trailing metadata lines are somewhat boilerplate but cheap and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter tool the description is thin: it omits the sidereal/tropical and ayanamsa choices that materially change results, and does not clarify the relationship to sibling phase/cycle tools. An output schema exists, so return values need not be explained, which keeps this at an adequate rather than poor level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 15 parameters and only 33% schema description coverage, the description carries real burden, yet it merely restates the four required fields already listed in the schema's required array. Eleven optional parameters (zodiacType, houseSystem, cosmogram, city, name, ayanamsaId, etc.) go unmentioned, and nothing explains why latitude/longitude matter for a phase calculation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (calculate) and resource (synodic phase of each planet relative to the Sun), and enumerates the eight phase names, so an agent knows exactly what is produced. It does not explicitly distinguish itself from close siblings like astroway_calendar_moon_phase or astroway_calendar_planetary_cycles, leaving the planetary-vs-lunar distinction to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description never says when to choose this tool over alternatives, nor does it exclude cases (e.g. single-planet phase vs moon phase). The bracketed metadata gives required inputs and a cost tier, which is operational context rather than usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context the annotations do not carry: endpoint, required params, and a cost of 50 credits (Tier 3), which materially affects tool selection. It omits any pagination/max-range behavior, hence not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence that front-loads the resource and semantics, followed by a compact structured metadata block. No filler prose, though the parenthetical shadow definitions make the opening sentence long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained (though shadow boundaries are helpfully clarified), and annotations cover the safety profile. Cost, endpoint, and required params round out selection-critical context; only pagination/max date-range behavior is unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 40%; `planetIds` and `startDate`/`endDate` lack schema descriptions. The description compensates partially by documenting the `planetIds` default (Mercury) and tying inputs to a date range, but says nothing about `fields`, `precision`, or input format beyond what the schema patterns show.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (retrograde periods) with scope (planets in `planetIds`, default Mercury, within a date range) and even lists the returned stations and shadow boundaries. An agent can distinguish this from siblings like moon_phase or ingresses. It stops short of naming a sibling alternative, so it is not a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what it returns but gives no when-to-use guidance, no exclusions, and no pointer to a related sibling (e.g. solar/lunar phase tools). The only usage signal is the implied 'provide a date range', which is already dictated by the schema's required fields.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: the credit formula (15 + ceil(chars/40)), the 3000-char cap, and the glossary-pinning behavior. Minor caveat: it says 21 languages while the schema enum lists 20, and the cost line contradicts its own formula.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is front-loaded with the core purpose and constraints, and the bracketed metadata lines convey required params and cost compactly. No wasted prose, though the metadata block and the duplicate/internally-inconsistent cost figures add slight noise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the description supplies cost, length limits, and the source-language default. The main gap is the completely unexplained 'domain' parameter, which is central to the astro-glossary feature.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, so the description must compensate and only partly does: it clarifies source_lang defaulting to English and the text length cap. The 'domain' enum (vedic/western/tarot/etc.) is undocumented in both schema and description, leaving the glossary-selection parameter opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('Translate one text') with the distinguishing traits of the astro variant: astrology-domain glossary pinning and single-text scope. That implicitly separates it from the sibling translate_batch and translate_glossary_lang tools, though neither sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives the source-language default and how to override it ('pass source_lang'), which is a useful usage hint. However, it never says when to choose this over translate_batch or translate_glossary_lang, so the agent is left to infer routing from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is covered. The description adds genuinely useful behavioral facts beyond that: per-item and total size ceilings (2000/20000 chars), the credit formula, and the rule that all items must share one target language and domain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and dense with the limits and pricing an agent needs. The trailing metadata block repeats information already in the schema ('Required: items, target_lang') and gives a flat '16 credits' figure that loosely duplicates the formula, but it stays short and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the cost/size limits are present. Missing for a batch operation: what happens on per-item failure, whether domain defaults, and how this tool relates to its translation siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (fields and precision), so the description carries partial burden. It clarifies items limits and the shared target_lang/domain constraint, which is meaningful, but says nothing about source_lang (auto-detect?) and leaves precision/fields entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Translate up to 25 strings') plus hard scope limits, so the batch nature is unambiguous. It does not, however, distinguish itself from the sibling translate tools (translate_astro, translate_glossary_lang, translate_languages), which an agent must infer on its own.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The constraints ('sharing one target language + domain') hint at the intended input shape but the description never says when to pick this tool over the sibling translation tools or when to fall back to a single-string call. No exclusions, prerequisites, or alternatives are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds cost information but then contradicts itself: "Free (0 credits)" versus "see your plan — endpoint not in the public credit manifest," which leaves the agent unable to state the cost reliably.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and tight, but the trailing metadata block is padded with redundant bracketed lines ([Required: lang] restates the schema, the endpoint line restates the name) and the self-contradictory cost note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, but the definition still leaves the agent with wrong parameter names and an unresolved cost question for what is otherwise a simple read endpoint.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description documents ?source and ?domain query parameters that do not exist in the input schema (which has only lang, fields, precision). This actively misleads the agent about the callable parameters, offsetting the otherwise complete schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Download the astrology glossary") scoped to a target language, so the agent knows what it fetches. It does not, however, distinguish itself from the sibling localization tools (translate_astro, translate_batch, translate_languages), leaving the agent to infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance and no comparison to the three sibling localization endpoints. The only routing-adjacent information is default values (source=en, domain=generic), which does not tell the agent when this tool is the right choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds cost context, but that context is self-contradictory: the header says "Free (0 credits)" while the trailing bracket says "see your plan — endpoint not in the public credit manifest." An agent cannot tell whether this call is free or metered, which undercuts the one behavioral fact the description tries to add.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is tight and front-loaded and is the only sentence that matters. The bracket block restates group and endpoint metadata the agent already has from the tool name and transport, and its cost line duplicates and contradicts the "Free (0 credits)" claim above it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-required-parameter reference endpoint with full annotations and an output schema, the description covers what is needed; the return shape is described by the schema, not the text. The only completeness blemish is the conflicting cost statements, which leave the agent uncertain about billing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters (fields, precision compact-mode controls) are fully documented inline, so the baseline is 3. The description contributes nothing about these parameters, but it does not need to.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with an exact cardinality: "List the 21 supported language codes + names." An agent immediately knows this is a static reference lookup. It does not, however, explicitly distinguish itself from the nearby siblings translate_glossary_lang, translate_astro, and translate_batch, which are the tools an agent might realistically confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The "Free (0 credits)" note implies this is a cheap, safe discovery call to make before a translation tool. But there is no explicit when-to-use statement, no pointer to translate_astro/translate_batch as the follow-up, and no exclusions. Usage is implied rather than guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is low; the description still adds real value by clarifying that endpoints are NOT invoked and that results are cached with a 5-minute TTL. It also discloses the return shape (total + per-endpoint breakdown with tier annotations), which is meaningful since no output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core capability and the non-invocation guarantee, followed by workflow guidance and the cache note. Nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description explains the return value, and the invocation-free and cache behaviors are covered. For a one-parameter, read-only estimator this is fully sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'endpoints' parameter is fully documented with examples and the leading-slash rule in the schema. The description only restates 'one or more endpoints' without adding format or constraint detail beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Estimate the credit cost of one or more endpoints') and immediately pins the scope with 'WITHOUT invoking them', which no sibling tool does. An agent can distinguish this from the many invocation/report siblings at a glance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit workflow guidance: 'estimate first, ask user confirmation, then invoke' for multi-step planning. This is clear when-to-use context, though it names no alternative tool or when-not-to-use condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, idempotentHint=true, and non-destructive behavior, so the safety profile is clear. The description adds the contextual detail that it computes a dignity score across key chart positions, but doesn't disclose behavioral traits beyond what annotations provide, such as response format or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the core purpose. The additional metadata (group, endpoint, cost) is useful context but slightly dilutes conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the annotations cover safety and idempotency, the schema is rich with 100% coverage, and an output schema exists, the description adequately defines the tool's purpose. It could be more complete with usage guidelines, but it's sufficient for an agent to understand what the tool does and how to call it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all parameters. The description doesn't add any parameter-level meaning beyond what's in the schema, which is expected given the high coverage, making a baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (Calculate) and names the exact astrological concept (Almuten Figuris), defining it as the planet with the highest essential dignity score across key chart positions. This clearly distinguishes it from siblings like astroway_dignities_essential_dignities and astroway_dignities_hyleg.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as essential_dignities or hyleg. While the concept definition implies its purpose, there are no explicit when-to-use or when-not-to-use statements.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe, idempotent, non-destructive read, so the safety profile is covered. The description adds a conceptual definition of what a disposition chain is, which is useful, but it does not disclose the POST-with-body shape, that this is a computed result and not a stored resource, or anything about the cost tier beyond the bracketed metadata line.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The prose is one efficient sentence, front-loaded with the action. The trailing bracketed metadata block (group/endpoint/cost) is structured and skimmable rather than wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-purpose computed chart tool with a rich schema and an output schema, the definition is minimally adequate. It defines the concept, which is the main non-obvious piece, but omits any cue about when this is the right tool versus the sibling dignities endpoints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema carries the parameter burden and the baseline of 3 applies. The description adds no parameter meaning beyond the one concept term ('sign rulers'), leaving mode/rulerMode semantics to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — 'Calculate planetary disposition chains' — and defines the concept inline ('the recursive sequence of sign rulers leading to the final dispositor'). This clearly distinguishes it from sibling tools like astroway_dignities_almuten (a single almuten winner) and astroway_dignities_disposition_chains_layout (a rendering of the same chains).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no when-to-use guidance, no prerequisites, and never names an alternative. An agent choosing among the many dignities siblings gets only the noun phrase to go on.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds useful operational context the annotations lack: group, endpoint, and a 20-credit Tier 2 cost. It does not describe the coordinate space, units, or determinism of the layout, which would have been genuinely valuable for a layout-computing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One tight sentence plus three compact bracketed metadata lines; the purpose is front-loaded and nothing is wasted. Slightly terse given the amount of schema complexity being invoked.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the params are fully documented in the schema. The cost/endpoint metadata is a plus. The main shortfall is that it never clarifies that the input is natal data plus a dispositor mode, leaving the agent to infer the call shape entirely from the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter in depth (timezone, ayanamsa, houseSystem, fields, precision). The description adds nothing about parameters, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Return) and resource (disposition chains) plus the distinguishing output feature: computed x/y layout coordinates for graph visualization. This differentiates it from the sibling astroway_dignities_disposition_chains without naming it, since the layout-coordinate qualifier is the differentiator, but the separation is left implicit rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, or alternative routing is given. The phrase 'for graph visualization' implies the intended consumption context, but the agent is not told when to pick this over the plain disposition-chains sibling or the render_* tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds the cost (20 credits, Tier 2) and the endpoint, which is useful operational context. It does not describe what the response contains or whether the analysis is deterministic, but with annotations carrying safety the bar is lower.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core description is a single tight sentence that front-loads the verb and the exact output. The group/endpoint/cost metadata is compressed into bracketed lines. No wasted prose, though the description is quite short relative to the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the description need not explain return values, and annotations cover safety. The cost and endpoint are disclosed. However, for a tool that sits among many sibling dignities tools, the description lacks differentiation guidance, and it does not mention that custom terms/decans tables can be supplied to override defaults, which is a meaningful capability present in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the body, fields, and precision parameters richly documented, including custom termsData and decansData tables. The description adds essentially no parameter-level detail beyond what the schema provides, but the schema already does the heavy lifting, so the baseline is high. It does not clarify which birth-data fields matter most for dignity calculation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (calculate) and resource (the five Ptolemaic essential dignities plus debilities) for each planet. It enumerates the five dignity types, which is more specific than most siblings. However, it does not differentiate itself from closely related siblings such as astroway_dignities_almuten or astroway_dignities_receptions, which an agent must distinguish among.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, no stated alternative, and no conditions for choosing this over the sibling dignities tools. The grouping tag '[Group: Dignities & Receptions]' and endpoint line imply context but do not tell the agent which sibling to pick. Usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful non-schema behavior: the endpoint path and a 20-credit Tier 2 cost, which lets an agent budget before calling. It still says nothing about auth or failure modes, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence carries the whole purpose, followed by short bracketed metadata lines for group, endpoint and cost. No filler or repetition, though the metadata block is largely boilerplate that could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the input schema is thorough. For a specialized Hellenistic calculation the description is minimally viable: it never notes what inputs are required for a valid Hyleg/Alcocoden determination or any limitations of the method, leaving that entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the nested birth-data schema documents date/time/coordinates, timezone, houseSystem and the compact-mode fields in detail. The description contributes no parameter meaning of its own, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Calculate) plus two named resources (Hyleg/apheta, Alcocoden) with brief glosses of each, and pins the method to traditional Hellenistic practice. This clearly separates it from the other dignity siblings (almuten, essential dignities, receptions), though it never names an alternative explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use statement, no prerequisites, and no mention of alternatives among the many dignity/calculation siblings. The Group tag and POST endpoint imply context but give the agent nothing actionable about selecting this tool over astroway_dignities_almuten or astroway_dignities_essential_dignities.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered structurally. The description adds genuinely new behavioral context beyond the annotations: the cost ('20 credits, Tier 2') and the transport endpoint (POST /v1/receptions), which affect whether an agent should call it. It does not describe latency or pagination, but neither is implied for a bounded two-planet-pair scan.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence of substance plus three short bracketed metadata lines (group, endpoint, cost). Nothing is repeated or padded, and the operative definition is front-loaded ahead of the metadata.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a computation over birth data; the input schema is exhaustively documented and an output schema exists, so return values need no explanation. What is missing is a note that required birth data (date, time, latitude, longitude) must be supplied and how this differs from the sibling dignity tools, but the definition is otherwise sufficient to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the nested body schema documents date, time, latitude, longitude, timezone, ayanamsa, houseSystem, plus the compact-mode fields/precision options in detail. The description contributes nothing about any parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Find mutual receptions between planets') and then defines the astronomical condition precisely ('pairs where each planet is in a sign ruled, exalted, or in the dignity of the other'), so an agent knows exactly what output to expect. It does not name or contrast with close siblings such as astroway_dignities_essential_dignities or astroway_dignities_disposition_chains, which is the only thing keeping it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance. The definition explains the underlying concept but never says to prefer this over essential dignities or disposition chains, and no trigger condition (e.g. 'use when the question concerns two planets exchanging sign rulership') is stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds operational context the annotations do not: the endpoint (POST /v1/acg) and the 50-credit Tier 3 cost, which is decision-relevant for an agent managing budget. It says nothing further about result size or line output, but the output schema covers that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One substantive sentence, front-loaded with the action and scope, followed by compact bracketed metadata (group, endpoint, required params, cost). No filler and nothing redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter calculation tool, the definition says almost nothing about the optional inputs that materially alter the result, nor which chart/coordinate conventions apply. The output schema excusably covers return values, but the description leaves an agent unable to configure the call beyond the bare required four fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% across 15 parameters, so the description carries the burden of compensation and does not meet it. It merely repeats the four required fields already declared in the schema and never mentions the impactful optional inputs (zodiacType, houseSystem, ayanamsa, timezone/timezoneOffset) that change the computed lines.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Calculate A*C*G lines for all planets') and glosses what those lines are, so the agent knows exactly what is produced. It does not, however, distinguish itself from nearby siblings such as astroway_geo_acg_line_report, astroway_geo_solar_acg, or astroway_geo_acg_best_places, which all operate in the same A*C*G space.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to choose this tool over the other geo/ACG siblings, and no exclusions or prerequisites are given. The cost line ('50 credits, Tier 3') hints at a budget consideration but is not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioural context: the bundled GeoNames set is 34,028 places above 15,000 people, and supportive and challenging totals are returned separately with each contributing line and its distance. It does not cover rate limits or auth, but the search-space scope is genuinely valuable and not derivable from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The leading sentence is well front-loaded, but the second sentence spends substantial length on spherical-geometry mechanics ('the distance to a horizon line IS the altitude in degrees of arc, and a meridian line offset is the hour angle times cos(latitude)') that does not help an agent decide to call the tool or how to invoke it. The dataset-size sentence does earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, and the description still adds ranking semantics and dataset scope. Combined with a 100%-covered schema that points to GET /v1/acg/categories for valid category values, an agent has what it needs. Only the sibling differentiation gap keeps it from being fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents category, sort, orbKm, minSeparationKm, limit, countries and precision in detail. The description adds no parameter-level syntax or defaults beyond what the schema provides. Baseline 3 applies when structured fields carry the full parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource: 'Rank cities against the astrocartography lines of a chart for one of the 19 life categories.' An agent immediately knows this returns a ranked city list for an ACG life category. It does not, however, distinguish itself from the very similarly named sibling astroway_geo_acg_by_category, so the sibling differentiation half of the criterion is unmet.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance and no mention of alternatives, despite several close siblings (astroway_geo_acg, astroway_geo_acg_by_category, astroway_geo_acg_zones). The 50-credit Tier 3 cost is disclosed, which is useful for budgeting, but nothing tells the agent whether to reach for this tool or a cheaper sibling. Usage is only inferable from the description of what gets returned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.