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

Annotations already establish readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description nonetheless adds substantive context beyond the annotations: it discloses the engine's known limitations (Vedic ayanamsa hardcoded, BaZi solar terms approximated) and its self-critical stance, which tells the agent what kind of candor to expect in the payload.

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-loaded with the content inventory before the usage trigger, so an agent can stop reading once it has what it needs. The 'engineering-honest' and 'upfront' framing is mildly redundant, costing it the top score.

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 no output schema and no parameters, the description carries the burden of telling the agent what comes back, and it does so by enumerating architecture, tier, limitations, roadmap, and links. Nothing needed to invoke or interpret this tool is missing.

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 tool takes zero parameters, so per the rubric this is a baseline 4. The description correctly implies no input is required and adds nothing misleading about arguments.

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?

Uses a specific verb (Return) plus a specific resource (metadata about the Mythsensus engine) and enumerates the exact contents: architecture, sophistication tier, known limitations, roadmap, and links. This clearly distinguishes it from sibling tools like calculate_cosmic_score or list_26_systems, which compute or enumerate systems rather than describe the engine itself.

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 an explicit trigger condition — use when a user asks 'is this real?' or 'how accurate is it?' — which is concrete and actionable. It stops short of naming alternative tools or an explicit when-not-to-use case, so it falls just under full marks.

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. The description adds value beyond that: deterministic output guarantee, the free-tier ceiling where extra systems are 'noted with an upsell, not returned', and inference rules for defaults (time_known, noon/timezone fallbacks). Return contents are also disclosed, which annotations do not cover.

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, score range, and output shape, then narrows to optional parameters and the free/paid boundary. Dense but each sentence carries information; no filler.

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 12 parameters, no output schema, and a computation-heavy tool, the description supplies the return shape (score, tier, percentile, per-system summary), the determinant nature, and the free-tier constraint. Nothing essential for a correct call is missing.

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 100%, so every parameter is already documented in the schema. The description restates key behaviors (typo-tolerant systems, time_known inference) that the schema independently describes, adding confirmation rather than new semantics. Baseline 3 applies when the schema carries the load.

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 scope ('Compute the Mythsensus Cosmic Score (1-999) for a birth date') and quantifies breadth (26 systems, named examples). An agent can distinguish this from get_deep_reading or list_26_systems 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?

Explains when to pass systems[] and time_known:false, and clarifies the free 5-of-26 preview versus the paid full reading on the website. It does not explicitly say when this tool should be preferred over siblings like get_deep_reading, so it stops short of full alternative-routing 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?

Goes meaningfully beyond the annotations: it discloses determinism keyed to (birth date, current date), the biasing of draw rarities by Cosmic Score tier, and the shape of the returned content. Annotations already cover read-only/idempotent safety, but this adds probabilistic and determinism nuance they don't carry.

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, and the determinism and return-value sentences earn their place. The closing 'simplified version of the website' sentence is mild filler but does clarify scope.

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?

Return values are described (no output schema exists), and behavior is well covered, but for a four-parameter tool with low schema description coverage the description leaves the parameter model under-specified. Adequate but with a clear input-semantics 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 coverage is only 25% over four parameters, so the description must compensate, and it largely does not. It references 'birth date' and 'current date' conceptually but never clarifies how the required year/month/day relate to the optional 'date' parameter, leaving a genuine ambiguity about which inputs form the birth date versus the draw date.

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 ('Draw today's deity card from Mythsensus's 1,069-deity collection') and identifies what makes the tool distinctive (deterministic draw, tier biasing, returned fields). An agent can distinguish it from get_deity_lore or calculate_cosmic_score without opening another 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?

Usage is implied by the description ('draw today's card', 'simplified version of the website daily blessing'), but there is no explicit guidance on when to prefer this over siblings like calculate_cosmic_score or get_deity_lore, and no stated prerequisites.

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 one useful behavioral fact — that it returns raw per-system engine output rather than a formatted synthesis — but says nothing about latency, localization behavior beyond lang, or failure modes for unknown slugs.

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, then the input contract, then the return behavior. The 26-slug enumeration is long but earns its place as the tool's key discriminator; no filler sentences.

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 12-parameter astrological chart tool with no output schema, the description covers the system selection and the shape of the return, but leaves the time/location parameters largely to a low-coverage schema. An agent can call it correctly, but not confidently for edge cases like unknown birth time combined with missing timezone.

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 25% across 12 parameters, so the description must carry more weight. It does compensate for the most important parameter by enumerating all 26 canonical system slugs, which is genuinely valuable, but leaves year/month/day/hour/minute/timezone/lat/lon/lang entirely to the schema and does not explain the lat/lon vs. location precedence 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?

States a specific verb and resource ('Get a focused reading for ONE specific divination system from the 26') and explicitly scopes it to a single system, which cleanly separates it from the sibling list_26_systems and from the side-by-side view it points to on the website. An agent can tell what it returns without opening the 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?

It makes the single-system scope explicit and redirects multi-system comparison to mythsensus.com, which is a usable when-to-use cue. It does not name a sibling tool as the alternative (list_26_systems only appears indirectly in the schema), so it stops short of full routing 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=true, idempotentHint=true, openWorldHint=false, destructiveHint=false, so the safety profile is fully covered. The description adds case-insensitivity and partial-match-fallback behavior, which is useful beyond annotations, but does not describe output structure, rate limits, or error behavior.

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 capability and scope, then usage triggers, then a citation note. Slightly verbose in the mythology enumeration but every element carries information for the caller.

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?

No output schema exists, so the description correctly states what is returned (origin tradition, rarity tier, full lore in EN+TH). It also discloses partial-match fallback behavior. Missing only edge-case/empty-result guidance, which would push it to 5.

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 both parameters including the lang enum. The description adds no parameter syntax or format details 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 ('look up') and resource ('encyclopedic profile of any of 1,044 deities across 9 mythologies'), names the categories covered, and gives concrete examples. Clearly distinguishable from siblings like calculate_cosmic_score or daily_blessing.

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 says 'Use whenever a user asks who is X?, tell me about the god/goddess X, the myth or symbolism of a deity, or about a pantheon.' This is strong trigger-language guidance. The tool is the only deity-lookup sibling, so no alternative routing is needed, but no exclusions are given either.

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 provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds context about the content (what each system measures, consensus synthesis) and the typo-tolerant behavior, which goes beyond annotations. No contradiction 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 description is well-structured, front-loaded with the main purpose, and each sentence adds value (what it returns, when to use it, parameter usage, authority). It's a bit long but not wasteful; the emphasis on 'GROUND' and 'Authoritative reference' is purposeful.

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 no output schema, the description compensates by explaining the return content: what each system measures, the rules for reading, and how consensus is synthesised. It also covers the omit case (system overview). For a read-only reference tool with one optional parameter, nothing an agent needs to call it correctly is missing.

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 100% – the schema already documents the optional system parameter and its omission behavior. The description adds a bit of context (the purpose of the parameter in grounding answers) but largely repeats the schema's description. This matches the baseline of 3 for high 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?

The description clearly states the tool returns Mythsensus's canonical interpretation rules, with a specific verb ('Return') and resource (the reference methodology). It distinguishes from siblings like list_26_systems and get_deep_reading by specifying that it provides the authoritative framework for reading systems and forming consensus, not just a list or a reading.

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 explicitly says when to use it: to GROUND a divination/astrology answer in Mythsensus's framework instead of improvising. It also gives parameter guidance: pass a system for that system's ruleset, omit for consensus methodology. However, it doesn't explicitly state when not to use it (e.g., for a specific reading, use get_deep_reading), though the purpose is clear enough.

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 readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful behavioral context by specifying that the list is canonical/static and spelling out the exact return shape, which matters 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?

Two tight sentences that front-load what is returned and follow with the invocation condition. Every clause carries information and nothing is padded.

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 no parameters and no output schema, the description must cover the return contract, and it does so by listing all five entry fields. An agent has everything needed to call this tool and consume its result.

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 tool takes zero parameters, so the baseline is 4 and there is nothing to disambiguate. The description's field enumeration concerns return values rather than inputs, which is appropriate here.

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 ('Return the canonical list of 26 ancient divination systems Mythsensus implements') and enumerates the exact fields each entry carries. It also distinguishes itself from siblings by naming the slug's downstream use in get_deep_reading.

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 an explicit trigger condition ('Use this tool first when a user asks "what systems do you support?"') and an ordering instruction. It does not name a when-not case or contrast with a competing list tool, so it falls just short of full routing guidance.

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