Sahadeva

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 structurally. The description adds no behavioral context at all — nothing about inputs' sensitivity, computation, or output shape — so it contributes nothing beyond 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?

It is a single front-loaded sentence with zero waste, so it is concise, but the conciseness comes from under-specification rather than discipline. There is no structure to organize because there is no content.

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 safety. However, for an 8-parameter tool with low schema coverage and a large ambiguous sibling set, the absence of any usage, parameter, or behavioral context makes the definition materially incomplete.

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 8 parameters and only 38% schema description coverage, the description is obligated to compensate for undocumented parameters such as name, date, and time. It supplies no parameter information whatsoever, leaving latitude/longitude/timezone/place semantics 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?

Tautological: description restates name/title.

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 guidance on when to use this tool rather than analyze_marriage_structure, analyze_property_and_vehicle, or the many other analyze_* siblings. No prerequisites, exclusions, or alternatives are named.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The only added claim, "without deterministic outcome claims," hints at an epistemic/ethical constraint on the output but is too vague to be actionable; nothing is said about computation scope, required inputs, or how results are sourced.

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?

It is short, but brevity here reflects under-specification rather than conciseness: the single sentence is grammatically garbled ("Evidence-linked analyze career structure") and no sentence earns its place by conveying usable information. There is no front-loaded statement of what the tool returns.

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 10-parameter tool with only 30% schema coverage, a required name/date/time triple, and an either/or location requirement, one vague sentence is wholly inadequate. Although an output schema exists (so return values need not be described), the description omits everything an agent needs to invoke 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 only 30% and the description adds zero parameter information, so the documentation burden falls entirely on the schema, which leaves latitude/longitude, asOfIso, timezoneOffset semantics and the anyOf place-vs-coordinates rule largely implicit. The description does nothing to compensate for this coverage gap across the 10 parameters.

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?

"Evidence-linked analyze career structure without deterministic outcome claims" essentially restates the tool name and title rather than describing what the tool actually produces. It never says this is a Jyotish/astrological career reading, what inputs drive it, or what the analysis contains, so it does not distinguish it from siblings like analyze_finance_structure or analyze_education_structure beyond the word "career".

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 (birth name/date/time required), no exclusions, and no pointer to an alternative sibling tool. The single sentence offers no routing information an agent could act on when choosing among the many analyze_* 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 cover the safety profile (read-only, idempotent, closed-world), so the bar is lower. The description still adds real behavioral context beyond them: it declares the pipeline deterministic, enumerates the evidence artifacts (supporting/opposing evidence, Varga confirmation, Dasha activation, uncertainty, citations, unresolved source keys) and, importantly, explicit abstention boundaries.

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 sentences, front-loaded with the core action, then the return contents, then a brief positioning line. Mostly efficient, though the enumerated return list is a dense dump that partly duplicates the output schema.

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 restated, yet the main gaps remain: no routing guidance versus the topic-specific siblings and no parameter semantics for 12 params at 0% schema coverage. It is adequate for a generic pipeline but leaves the agent under-informed.

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 0% across 12 parameters, so the description must compensate and largely does not. It only gestures at the topic values and even omits 'wealth'; it says nothing about name/date/time/place vs lat-long/timezone alternatives, asOfDate, language, or birthTimeAccuracyMinutes.

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 ('Runs the shared deterministic judgment pipeline') scoped to named topics, so the agent knows it produces a topic-level judgment. It does not distinguish itself from the many topic-specific siblings (analyze_career_structure, analyze_marriage_structure, etc.), and it lists five topics while the enum also allows 'wealth', a small inaccuracy.

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/when-not guidance and no named alternative across ~50 siblings. An agent cannot tell whether to call this generic topic pipeline or the dedicated analyze_*_structure tools for the same subject.

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. The description adds a meaningful behavioral constraint beyond those structured hints: the analysis is 'evidence-linked' and avoids 'deterministic outcome claims,' which tells the agent the output framing is probabilistic rather than predictive.

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 definition is short, but it is an under-specified fragment rather than a structured description. It front-loads 'Evidence-linked' awkwardly and does not provide enough context to be useful, so brevity here reflects omission rather than efficient 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?

Although an output schema exists and annotations cover the safety profile, the description still leaves major gaps for a 10-parameter analysis tool with low schema description coverage. It omits usage guidance, parameter explanations, and any indication of required inputs such as date, time, and location data.

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 does not mention any of the 10 parameters, and schema description coverage is only 30%. For a tool requiring name, date, time, and either place or latitude/longitude/timezone, the description provides no additional meaning about parameter usage or constraints.

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 verb ('analyze') and resource ('education structure'), so the general action is clear. However, it does not distinguish this tool from siblings like analyze_career_structure or analyze_finance_structure beyond the topic word, and the phrasing is awkward.

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, nor any prerequisites or exclusions. The only usage-adjacent statement is the epistemic caveat about avoiding deterministic outcome claims, which is not a selection guideline.

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 safe-read profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the description's added burden is light. The phrase "without deterministic outcome claims" does convey that results are framed as evidence-linked rather than predictive, which is meaningful for a jyotish tool, but it discloses no concrete behaviors such as required inputs, failure modes, or how topics constrain the analysis.

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?

It is a single short sentence, which is efficient, but the brevity comes from under-specification rather than tight editing. Nothing is padded, yet the one sentence carries almost no information beyond the tool name.

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?

This is a complex tool with 10 parameters, an anyOf requirement for place-or-coordinates, and topic selection, yet the description never addresses required inputs or invocation context. The output schema exists so return values need not be explained, but the input-side gaps leave an agent without enough 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 30% across 10 parameters, so the description should compensate and does not — it explains nothing about name, date, time, the place/coordinates alternatives, or the topics enum. The only marginally documented parameters (place, timezone, timezoneOffset) are covered by the schema itself, not 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?

"Analyze finance structure" merely restates the tool name and title, and the only additional words are generic hedging ("evidence-linked", "without deterministic outcome claims"). An agent cannot tell from this what the analysis actually computes or how it differs from the many sibling analyze_* 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 when-to-use guidance, no mention of prerequisites (birth name/date/time plus place or coordinates), and no routing to alternatives among the numerous structural-analysis siblings. Nothing is misleading, but nothing is offered 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 declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds some genuine context beyond the schema by noting 'supporting and opposing evidence', 'unresolved source keys', and 'sensitive-house restrictions', hinting at output structure and handling caveats, but it says nothing about computational cost, required birth-data fidelity, 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?

A single long run-on sentence enumerating outputs; it is dense and wastes no words on fluff, but it is a comma-list rather than a front-loaded statement of purpose, which weakens structure.

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 natal-chart analysis tool with 9 parameters and an anyOf location constraint, the description is inadequate. Since an output schema exists it need not restate the return fields, yet it does only that while omitting the usage and parameter context an agent actually needs 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 33% across 9 parameters, so the description is expected to compensate — and it provides zero parameter guidance. It never explains the house selector, the birth date/time/name inputs, or the place-vs-coordinates alternative that the anyOf enforces.

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 name and title establish the operation (analyze one natal house), but the description itself opens with 'Returns...' and enumerates outputs rather than stating what the tool does. An agent gets the gist from name+title but not from the description text, and there is no differentiation from siblings like analyze_chart_topic or analyze_marriage_structure.

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 indication of when to use this tool versus the many other analyze_* siblings, nor any prerequisites or exclusions. Usage must be inferred solely from the tool 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 and non-destructive behavior, so the description is not burdened with safety disclosure. It adds real behavioral context by naming what is deliberately omitted (prediction prose, annual-chart emulation, remedies) and the gating conditions (atomic extraction, scan verification, lineage review).

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 packed sentences with the core operation front-loaded and the limitation clause second. Nothing is wasted, though the second sentence is dense and the tool's input requirements are never surfaced.

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 behavioral framing is adequate. For a chart tool whose input is governed by a non-obvious anyOf (place OR latitude/longitude/timezone) with six undocumented parameters, the description leaves the calling agent to infer input requirements entirely from a low-coverage 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?

Nine parameters with only 33% schema description coverage, and the description says nothing about name, date, time, the anyOf place-vs-coordinates constraint, or the timezone fallback. With coverage this low, the description is expected to compensate for the undocumented inputs and does not.

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 transformation ('converts verified natal placements to Lal Kitab fixed houses') and the return artifact ('source locators for all nine planet-house sections'), which sets it apart from neighbors like analyze_remedies and explore_lal_kitab_sources. It is clear, but it never names the sibling it should be preferred over, so it stops short of the top score.

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 withheld-qualities clause implies when this tool is appropriate (structural/source work rather than prediction) and effectively warns against expecting remedies or annual-chart output. However, it gives no positive 'use this when…' trigger and does not route the agent to an alternative tool.

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 a modest but real behavioral trait — that output is 'evidence-linked' and makes no deterministic outcome claims — which is beyond the annotations, though it is not elaborated (no mention of evidence format, sources, or limitations).

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?

It is a single fragment rather than an informative sentence; brevity here reflects under-specification, not efficiency. Nothing is front-loaded because there is essentially only one clause.

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. However, for a 10-parameter tool with low schema coverage, the description omits input requirements, the place/coordinates branch, and usage context, leaving it inadequate to invoke the tool confidently.

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 30% across 10 parameters, and the description adds nothing about any parameter. Required fields (name, date, time) and the coordinate-vs-place branching are left for the schema alone, leaving a substantial gap the description does not compensate for.

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 essentially restates the tool name/title ('analyze marriage structure') with a qualifier tacked on. It does not distinguish this tool from nearby siblings such as analyze_career_structure, find_marriage_windows, or get_marriage_readiness, so an agent cannot tell which marriage-related tool to pick.

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 named alternative. The phrase 'without deterministic outcome claims' faintly implies this is an evidence-based analysis rather than a prediction, but it gives no actionable 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, destructiveHint=false, and openWorldHint=false, so the safety and side-effect profile is fully covered. The description adds two useful behavioral constraints – outputs are 'evidence-linked' and avoid 'deterministic outcome claims' – but it says nothing about required input prerequisites, calculation assumptions, or result format.

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 entire description is a single awkwardly constructed fragment, 'Evidence-linked analyze nakshatra profile without deterministic outcome claims,' which is terse but under-specified rather than concise. It is front-loaded with the tool concept but omits the information an agent needs to invoke it correctly.

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?

This is a complex tool with 10 parameters and an output schema, yet the description does not explain what inputs are required, how the anyOf place-versus-coordinates constraint should be handled, or what the analysis covers. Because an output schema exists the description need not explain return values, but the input-side gaps leave it substantially incomplete.

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 schema has 10 parameters with only 30% description coverage, and several important parameters (name, date, time, topics, asOfIso, latitude, longitude) are undocumented. The description provides no additional parameter meaning, so it fails to compensate for the low 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 names a specific verb ('analyze') and resource ('nakshatra profile'), but it never explains what a nakshatra profile analysis includes or returns. With dozens of analyze_* siblings in the toolset, it also fails to distinguish this tool from related astrology analysis 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 guidance on when to use this tool, when not to, or how it relates to alternatives like analyze_chart_topic or calculate_devata_profile. The only usage-adjacent phrase, 'without deterministic outcome claims,' is a constraint on output framing, not a routing 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, covering safety and repeatability. The description adds one behavioral claim ('without deterministic outcome claims'), which is a useful constraint but only weakly one: it tells the agent not to expect definitive predictions but doesn't explain what evidence linkage looks like, what output format is produced, or whether topics filter the analysis.

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 short sentence with no filler, front-loaded with the verb. It's efficient, though the efficiency comes partly from under-specification rather than tight writing.

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 has 10 parameters, an anyOf location constraint, and sits among 40+ analysis siblings, but the description provides no help navigating any of this. Even with an output schema available (reducing the need to explain returns), the description is too thin to help an agent choose this tool or supply correct 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 30%, so the description must compensate for undocumented parameters, yet it adds nothing about 'topics', 'asOfIso', 'date', 'time', or 'name'. With 10 parameters and a required anyOf constraint (place OR lat/long/timezone), the description leaves all the parameter semantics to the schema, which is incomplete. This is below the baseline because the description fails to compensate for low 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 'Evidence-linked analyze property and vehicle without deterministic outcome claims' essentially restates the tool name 'analyze_property_and_vehicle' with a methodological qualifier. It does not distinguish this tool from the many sibling analyze_* tools (analyze_chart_topic, analyze_house, analyze_varga) that also perform property-focused analysis. While it does mention 'property and vehicle', it's unclear what analysis beyond the name is actually performed.

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 is provided. The description does not state when to select this tool versus analyze_chart_topic, analyze_house, or any of the other ~40 analysis siblings. No alternatives, no prerequisites, no exclusions.

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 this as a safe, read-only, idempotent operation, so the bar is lower. The description still adds real value beyond them: every candidate 'exposes its source and publication gate', and it explicitly withholds unreviewed gemstones, initiation-only mantras, fasting and costly rituals. That content-gating behavior is exactly the kind of trait an agent cannot infer 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?

Two sentences is a reasonable size for a tool of this complexity, and the withholding clause is well-placed. But the first sentence is a dense run-on list of jargon nouns that buries the primary purpose rather than front-loading 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 12-parameter tool with a nested preferences object, this description covers only the output-gating behavior; usage routing and parameter semantics are absent. With an output schema present it need not explain return values, but the missing when-to-use and parameter guidance leaves it incomplete for safe 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 25% across 12 parameters including a nested preferences object, so the description must compensate and largely does not. It gestures at 'belief/cost/burden preferences' and 'optional charity', which loosely map to allowCharity/allowPrayer/maximumCost/maximumBurden, but says nothing about the required place vs latitude/longitude/timezone disjunction, birthTimeAccuracyMinutes, asOfDate, or the enum meanings.

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 title names a concrete deliverable (a source-grounded chart remedy protocol) and the description enumerates the inputs it fuses (evidence ledger, preferences, Iṣṭa/Devatā, Muhurta routing). However the verb is 'combines', which describes pipeline stages rather than the output, and the heavy jargon (Iṣṭa, Devatā, Muhurta-as-remedy routing) leaves the core purpose somewhat abstract. It never distinguishes itself from the closely related sibling suggest_safe_practice.

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 use this tool, when to prefer an alternative, or any prerequisite beyond the implicit need for birth data. Siblings like suggest_safe_practice, calculate_devata_profile, and find_muhurta are obviously adjacent but are never referenced as alternatives or exclusions.

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 read-only, non-destructive, idempotent behavior. The description adds meaningful methodological context: 'evidence-linked' and 'without deterministic outcome claims.' However, it does not explain the analysis process, what evidence is used, or what the output contains beyond 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?

The single sentence is concise but severely under-specified for a complex analysis tool with 10 parameters. It largely repeats the title, so it does not earn its place as a useful definition.

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 crowded sibling set, 10-parameter schema, and output schema, the description is not complete enough for an agent to select or invoke the tool confidently. It omits purpose detail, usage context, and parameter guidance, though annotations and output schema cover some safety and return-value concerns.

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 has 10 parameters with only 30% schema description coverage, and the description provides no parameter information at all. It fails to compensate for the low coverage or clarify required inputs like name, date, time, place, coordinates, topics, or asOfIso.

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 mostly restates the tool name and title ('analyze spiritual path'), adding only a methodological caveat. It does not specify what aspects of a spiritual path are analyzed or distinguish this from the many sibling analyze_* 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 guidance on when to use this tool, when not to use it, or which sibling tools are alternatives. An agent cannot infer whether this is for initial exploration, deep analysis, or report generation.

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 covered. However, the description adds no behavioral context at all — not what 'activation' means, not the return shape, not whether all three models are combined or reported separately. It contributes nothing beyond 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?

The single sentence is short, but brevity here reflects under-specification rather than discipline. Every word is a duplicate of the title, so no sentence earns its place by conveying new 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 12-parameter, 7-required tool with only 25% schema description coverage, the description is entirely inadequate. An output schema exists, so return values need not be explained, but the input contract and the tool's distinction from numerous siblings are left completely 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 only 25% across 12 parameters, so the description must compensate, and it does not. Critical inputs like topic, asOfIso, startIso, endIso, name, date, and time are undocumented in both schema and description, and the description never mentions any parameter.

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?

Tautological: description restates name/title.

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 guidance on when to use this tool versus alternatives such as fuse_timing, calculate_dasha_system, or the topic-specific analyze_* tools. No prerequisites, timing, or exclusions are stated. The agent is left to guess 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, idempotentHint, destructiveHint=false and closed-world, so the safety profile is fully covered. The description adds essentially nothing beyond a hint that a single varga is analyzed; it says nothing about computation cost, required chart data quality, or output shape. It does not contradict 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?

It is short and front-loaded, but this is under-specification rather than conciseness: the single phrase simply repeats the title and earns no additional place in the definition.

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 10-parameter tool with a complex anyOf location branch, enum-constrained varga and topic, and an output schema, a four-word restatement of the title is wholly inadequate. An agent cannot determine inputs or expectations from the description alone.

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 30% across 10 parameters, so the description is required to compensate and does not. It never explains the varga enum, the place-vs-coordinates anyOf branch, or the meaningless-to-an-agent 'topic' enum, leaving key parameters undocumented.

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?

Tautological: description restates name/title.

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 guidance on when to call this versus analyze_chart_topic, analyze_house, or the many structure-specific analyzers. No prerequisites, no exclusions, no context about requiring accurate birth data.

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 covered by structured data. The description adds zero behavioral context beyond that — no note on what a 'yoga' analysis returns, what inputs it derives, or what happens with partial birth data.

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?

It is a single short sentence with no padding, but this brevity is under-specification rather than conciseness — it simply echoes the title. There is no front-loaded explanation of purpose, inputs, or usage.

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, but this is a fairly complex tool with an anyOf required-parameter branch and 8 parameters, and the description covers none of it. For an astronomical analysis tool with two distinct input modes, the description is materially incomplete.

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 38% across 8 parameters, and the description supplies no parameter meaning at all. It does not explain the anyOf branch (place-only vs latitude+longitude+timezone), the date/time format expectations, or the timezoneOffset fallback, 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?

Tautological: description restates name/title.

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 guidance on when to use this tool, when not to, or how it relates to alternatives. With many overlapping siblings (calculate_strength_profile, calculate_doshas, analyze_house), an agent has no way to know why it should pick this tool for yoga analysis over those.

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, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful context beyond them: gates are reported independently, and Lal Kitab is explicitly source-only until a dedicated reviewed engine exists, which sets accurate expectations about output 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?

Two front-loaded sentences with no filler; the five gate categories are listed compactly and the caveat follows. Slightly dense but efficient.

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 described, and annotations carry the safety profile. For a zero-param read tool, listing the gate categories plus the Lal Kitab caveat is sufficient 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool applies. No semantic gap exists.

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 verb (Reports) and resource (readiness gates) and enumerates the five gate categories it covers, so an agent knows exactly what the tool returns. It does not, however, position itself against lookalike siblings such as get_validation_report or audit_prediction_claim, so differentiation is left 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?

There is no explicit guidance on when to call this tool versus the many audit_* and get_* siblings, and no prerequisites or exclusions are stated. The agent must guess whether this is a pre-prediction gate check or a general validation report.

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 behavior. The description adds a useful limitation ('does not claim an external ephemeris recomputation') and pre-interpretation scope, but omits auth requirements, failure behavior, and data-source details beyond that caveat.

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 what the tool checks, followed by a clarifying caveat. No filler or repetition, and the structure is easy to scan.

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 schema exists and annotations cover safety, so return values need not be explained. But for a 9-parameter audit tool with 33% schema description coverage, the description omits parameter semantics and input-combination rules, leaving an agent under-informed about correct invocation beyond the general purpose.

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 9 parameters. The description mentions timezone provenance but does not explain name, date, time, place, latitude, longitude, timezoneOffset, or birthTimeAccuracyMinutes, nor does it clarify the place-versus-coordinates input pattern. It fails to compensate for the low 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 ('Checks') and specific resources (engine certification, timezone provenance, conventions, boundary distances). It distinguishes from external ephemeris recomputation, but does not explicitly differentiate from sibling audit/validation tools such as audit_prediction_claim or get_validation_report.

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?

Implies usage 'before interpretation' and states it does not recompute an external ephemeris, which gives some when-to-use context. However, it provides no explicit alternatives, exclusions, or conditions for choosing it over related audit and validation 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=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety/idempotency behavior is covered structurally. The description contributes the gate taxonomy and the three-valued verdict vocabulary (publish/caution/abstain), which is genuinely useful behavioral context, but it says nothing about preconditions, what the caller must supply for the gates to resolve, or what an abstain verdict implies.

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 with no filler or repetition, ending on the concrete outcomes. It is dense but every clause carries content; the only cost is that terseness makes it opaque 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?

An output schema exists, so return values need not be described, but a 10-parameter gate-evaluation tool with 0% schema coverage needs far more than one clause about which gates run. Missing are the meaning of the inputs, the required claim format, and any routing against the sibling audit/readiness tools. The description is insufficient for correct invocation even though the verdict vocabulary is present.

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 0% across 10 parameters, so the description carries the full burden and mostly fails it. The gate names hint at a few inputs (calculation→calculationCertified, approved-rule→approvedRules, opposition→opposingEvidence, harm→harmClass), but format, optionality, and the roles of claimClass, nearBoundary, unresolvedSourceKeys and supportingEvidence are never explained. With 0% coverage a 2 is generous but the implicit mapping does add a little signal.

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 concrete mechanism (five named gates) and concrete outputs (publish, caution or abstain), which tells an agent roughly what happens. However, it never states the resource being audited (a single prediction claim) or how it differs from the many adjacent audit/assess siblings such as audit_reading_evidence, audit_chart_calculation and assess_prediction_readiness. Purpose is inferable but not sharply differentiated.

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, when-not-to-use, or alternative-tool guidance anywhere in the description. Given the sibling list contains at least three other auditing/readiness tools, an agent has no stated signal for choosing audit_prediction_claim over them. Nothing in the text is misleading, but no routing help is offered.

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 covered. The description adds nothing beyond those annotations – it does not say what 'safety rules' are checked, what happens on failure, whether a text over the length limit is rejected, or how conflicting prose is reported. It is effectively a title echo rather than added 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?

It is a single, front-loaded sentence with no padding, which is structurally clean. But the sentence duplicates the tool title verbatim, so it does not earn its place by adding 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-value detail is not required, but this is a complex tool: dual input modes (place vs explicit coordinates), a 30,000-character prose payload, and an undefined notion of 'calculated placements'. None of that is explained. For a 9-parameter audit tool sitting among many similarly named audit/claim tools, the description is too thin to guide 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 33%, and the description supplies zero parameter meaning. The critical either/or contract – supply 'place' OR the latitude/longitude/timezone triple – is expressed only as an anyOf in the schema, and required fields name, date, time and text carry no explanation of expected formats (date/time string shape, timezoneOffset being a derived fallback). The description 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?

Tautological: description restates name/title.

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 stated preconditions (e.g. that placements must already be calculated before auditing prose), and no mention of alternatives such as audit_prediction_claim for single-claim checks or compare_reading_versions for version diffs. The agent must infer the trigger entirely 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered externally. The only behavioral addition is the vague phrase 'without deterministic outcome claims,' which hints at an output-epistemics policy but never specifies 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?

It is short, but the single sentence is almost a pure restatement of the name and title, so it spends its words on redundancy rather than front-loading any actionable 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 10-parameter tool with a complex conditional schema (place OR lat/long/timezone) and low description coverage, the description supplies none of the missing context about inputs or behavior. Even with an output schema present, this is far too thin.

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 10 parameters and only 30% schema description coverage, the description carries the burden of explaining the many undocumented inputs, yet it mentions none of them (name, date, time, topics, asOfIso, etc.). It adds zero meaning 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 restates the tool name almost verbatim ('build claim evidence ledger'), adding only the qualifier 'without deterministic outcome claims.' It never states what a 'claim evidence ledger' actually does or what input it consumes, so it is effectively tautological with the title.

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 differentiation from the many sibling analysis/audit tools (audit_prediction_claim, audit_reading_evidence, assess_prediction_readiness). An agent cannot infer from this text when this tool should be chosen over those.

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 openWorldHint=false, so the safety profile is covered. However, the description adds zero behavioral context — nothing about required birth inputs, determinism of the result, or what the calculation consumes — so it contributes nothing beyond 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?

It is short but by omission, not by economy — it is under-specified rather than concise, conveying no information an agent could act on.

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 complex Vedic calculation taking name/date/time plus a mutually exclusive location specification, and with 38% schema coverage, the description omits everything the agent needs to invoke it correctly. An output schema exists, so return values need not be covered, but the input side is entirely 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 only 38% across 8 parameters, including a non-obvious anyOf requiring either 'place' OR the 'latitude'+'longitude'+'timezone' triple. The description says nothing about any parameter, so it fails entirely to compensate for the undocumented majority.

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?

Tautological: description restates name/title.

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 (birth data), and no reference to alternatives such as calculate_strength_profile or render_chart. The agent gets no routing signal at all.

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 read-only, idempotent, non-destructive safety profile, and the description adds genuine behavioural context: it resolves both birth places, computes both charts, and returns 'auditable' breakdowns, while explicitly disclaiming any relationship verdict. It does not, however, note any cost, latency, or precision caveats despite the birthTimeAccuracyMinutes parameter.

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-packed sentences with the computation and the scope disclaimer front-loaded, no filler, and every clause carrying 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?

With an output schema present, return values need not be re-explained, and annotations cover safety. The description covers computation scope and the non-verdict framing well, but leaves the dual place/coordinate input modes unresolved for a fairly complex nested 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 low, and the awkward anyOf input modes (place vs latitude/longitude/timezone) plus birthTimeAccuracyMinutes are not clarified. The phrase 'Resolves both birth places' adds some meaning about how the 'place' field is treated as a lookup query, but the description largely leaves the parameter contract 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 (calculates/resolves) and resource (compatibility), and names the exact systems computed: North Indian 36-point Ashtakoota, South Indian ten-Porutham, and Mangal/Kuja Dosha evidence. This distinguishes it clearly from generic siblings like calculate_doshas or get_marriage_readiness.

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 scope caveat 'Traditional research preview; never a relationship verdict' implies research use, but there is no explicit when-to-use versus siblings such as get_marriage_readiness, find_marriage_windows, or analyze_marriage_structure. 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds nothing beyond that: no note that the requested Dasha period depends on asOfIso, no statement about whether results are deterministic given birth data, and no hint about the resolution strategy used when 'place' and explicit coordinates disagree.

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 single sentence is short but it is under-specified rather than concise — it consumes the whole description with text that duplicates the title and earns no place. There is no front-loaded distinction or actionable detail an agent could use.

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 10-parameter tool with 5 required fields, an anyOf location constraint, an enum selector, and 30% schema coverage, this description is completely inadequate. It leaves the agent unable to tell which system to select or how to satisfy the location requirements; only the presence of an output schema saves any part of the contract.

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 30%, and the description contributes zero parameter meaning. The 7 enum values for 'system' (vimshottari, yogini, ashtottari, kalachakra, narayana, chara, status) are unexplained, 'asOfIso' is never defined, and the anyOf branch logic between 'place' and latitude/longitude/timezone is left 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?

Tautological: description restates name/title.

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 guidance on when to invoke this tool versus the ~50 sibling tools, no prerequisites, and no mention of the alternative calculation endpoints. Nothing in the text helps an agent decide between this and, for example, calculate_gochara_from_known_place or calculate_strength_profile.

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), so the bar is lower, yet the description adds real behavioral context: the tie-break chain, the refusal behavior for unsupported lineages, and two explicit scope exclusions (no initiation-only mantra, no single uniquely correct deity). This meaningfully constrains interpretation of the output.

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 dense sentences with the computed outputs and method front-loaded and the scope caveats at the end. No filler, though the astrological jargon packs several clauses per 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 needn't be explained, and the safety profile is covered by annotations. But for a 10-parameter tool with low schema coverage, the description omits any guidance on the required name/date/time inputs or the coordinates-vs-place branch, leaving gaps an agent must resolve from the schema alone.

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 10 parameters and only 30% schema description coverage, the description should compensate, but it only gestures at the lineage preset and tie-breaks without explaining lineage enum values, the place-vs-coordinates duality, timezone handling, or birthTimeAccuracyMinutes. Most parameters remain undocumented in both places.

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 (calculates) and precisely enumerates the outputs: Iṣṭa, Dharma, Pālana, Guru and Kula Devatā anchors. It also names the method (lineage preset, occupants, Rashi Drishti, sign lord) which distinguishes it from siblings like analyze_spiritual_path or analyze_remedies.

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 implies when to use it (when an explicit lineage preset is available) and states that unsupported lineages are withheld rather than silently mixed, which is a useful boundary condition. However, it never names an alternative tool or tells the agent what to do when the lineage is unsupported.

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 safety and repeatability are covered. The description adds that output includes raw/effective severity and explicit cancellation or mitigation evidence, which is useful behavioral context beyond the annotations, but it does not discuss permissions, rate limits, or other operational 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 description is a single front-loaded sentence that leads with the verb and immediately enumerates the dosha types. It is dense but efficient, with no filler or redundant clauses.

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 10 input parameters, low schema coverage, and no usage guidance, the description is too thin for the tool's complexity. Although an output schema exists (so return values need not be explained), the description omits any explanation of input requirements, location handling, or when this tool is the right choice among many 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 30% across 10 parameters, and the description adds no parameter-level information at all. It does not explain the required name/date/time fields, the anyOf location requirement, the timezoneOffset fallback, or the language enum, leaving the schema's own gaps entirely unaddressed.

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 uses a specific verb ('Calculates') and names four distinct dosha patterns (Mangal/Kuja, Kaal Sarpa enclosure, Kemadruma, Pitru-related candidates), which tells the agent exactly what domain is covered. It does not explicitly differentiate from closely related siblings like analyze_yogas or calculate_strength_profile, so a 4 is appropriate.

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 no guidance on when to use this tool versus alternatives such as analyze_yogas or calculate_strength_profile. It only states what is calculated, leaving the agent to infer context from the name and sibling list.

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, destructive=false, and openWorldHint=false, so safety is covered. The description adds useful context that the tool performs a place/timezone resolution step before computation, but it says nothing about failure behavior for unknown place names, output determinism, or resolution errors.

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 with the distinguishing mechanic (verified catalogue place + IANA timezone) stated before the benefit clause. No wasted words, though it is dense enough that it reads as one packed clause chain.

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. However, for a four-required-parameter astronomical computation with 0% schema documentation, the description leaves the meaning of natalLagnaSign and the place-resolution contract unspecified, which is a meaningful gap 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 0% across five parameters, yet the description only gestures at "place" and hints at date/time implicitly through "transits". Critically, natalLagnaSign (a 0-11 sign index) and the language enum are never explained anywhere a caller can see. The description 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?

The description names a specific verb (calculates sidereal transits) and pins the key distinguishing mechanic: the place is a verified catalogue entry resolved together with its IANA timezone rather than raw coordinates. This separates it from generic transit tools like analyze_transit_activation, though it never names a 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?

"Avoiding manual coordinate and offset entry" implies the tool is the preferred path when the location is already in the catalogue, but there is no explicit when/when-not statement or guidance to call search_locations first for unverified places. 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 declare readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description adds useful context beyond that: it validates chart fitness (implying it may flag an unfit chart) and returns an auditable judgment. It still omits what happens on a failed fitness check or how place vs. explicit coordinates are reconciled.

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 with the core action front-loaded and no filler. It is slightly jargon-heavy ('outcome-confirmation hook'), but every clause carries 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-value explanation is not required, and the description notes the auditability of the result. For a complex 8-parameter tool with low schema coverage, though, the definition leaves key input decisions (location source, category choice) unguided.

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 38%, so the description is expected to compensate, and it does not. It provides no meaning for any of the 8 parameters and never clarifies how the place-only vs. latitude/longitude/timezone paths differ or what 'category' or 'language' affect.

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 verb (casts) and a specific resource (a server-time horary chart), then states the internal steps: fitness check and a structural judgment. 'Server-time' meaningfully scopes it apart from natal-chart siblings that rely on birth data. However it never names a sibling tool or explicitly contrasts itself with them, so it falls 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 or when-not-to-use guidance, and no alternative is named. The 'outcome-confirmation hook' hints at a follow-up with record_prashna_outcome but never says so, leaving routing entirely 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 declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description adds no behavioral context of its own — no cost, latency, computation scope, or failure modes — though it does not contradict 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?

The single sentence is too short to be wasteful, but this is under-specification rather than conciseness. It front-loads nothing because there is nothing to front-load.

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 an 8-parameter calculation tool with a rich anyOf location schema, a required identity/date/time triple, and a complex astrological domain, a bare title restatement is completely inadequate. An output schema exists (so return values need not be described), but input structuring and tool selection remain entirely unexplained.

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 38% across 8 parameters, so the description is obliged to compensate and it contributes nothing. It does not explain the anyOf branch (place vs. latitude/longitude/timezone), the required name/date/time triple, or the timezoneOffset fallback.

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?

Tautological: description restates name/title.

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 prerequisites, and no mention of any alternative tool. Among ~50 calculation and analysis siblings, an agent has no basis for choosing this tool over calculate_ashtakavarga or analyze_nakshatra_profile.

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 still adds real behavioral value: it discloses that it flags when a Lahiri judgment must not be reused and that alternative full derived charts stay explicitly unvalidated, which is meaningful limitation context beyond 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?

Two tight sentences, front-loaded with the core comparison action before the anchor details and the validation caveat. Dense but every clause 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?

An output schema exists, so return values need not be described, and annotations cover safety. However, with 10 parameters and zero schema coverage, the description leaves the anyOf location input and timing parameters unexplained, which is a real gap 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?

With 10 parameters at 0% schema description coverage, the description carries the full documentation burden but documents almost nothing. It references 'topic' and 'selected alternative ayanamsa projections' (conventions), but never explains the place-vs-lat/long/timezone anyOf, timezoneOffset, or the convention enum values, leaving the schema 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?

States a specific verb (compares) and resource (Lahiri vs alternative ayanamsa projections for one topic), and enumerates the anchors it checks (Lagna, topic lord, karaka, sign, house, Nakshatra). It is clear what the tool does, though it never names the close siblings compare_traditions or compare_reading_versions to differentiate 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?

The phrase 'for one topic' and 'marks when a Lahiri judgment must not be reused' imply the context of use, and the unvalidated-charts caveat hints at boundaries. But there is no explicit when-to-use instruction or routing against the alternative comparison tools, so usage must be 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 establish the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description is not the primary carrier of behavior. It usefully adds that the comparison covers engine, ruleset, input and conclusion status, but says nothing about output shape, size, or whether versions must be ordered.

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 with zero waste, though it is terse to the point of under-specification rather than disciplined brevity.

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 tool taking two required nested objects at 0% schema coverage, the description leaves too much unsaid: no parameter guidance, no usage context, and no note on version ordering. The existing output schema spares it from explaining return values, but that alone does not rescue completeness.

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?

Both required parameters are bare nested objects with 0% schema description coverage, and the description never explains what 'first' and 'second' should contain or how the nested fields map to the compared dimensions. With full schema burden on the description and no compensation, this is a clear 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 names a specific verb ('compares') and enumerates the comparison axes (engine, ruleset, input, conclusion status), which pairs with the tool name to make the resource clear. It does not, however, distinguish itself from sibling comparison tools like compare_conventions or compare_traditions.

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 this tool should be used, what triggers a version comparison, or which alternatives exist. The agent must infer the scenario entirely 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, closed-world behavior. The description adds genuine context beyond that: the comparison preserves separate methods, evidence, contradictions and readiness states, i.e. it does not fuse outputs. It says nothing about output shape, ordering, or failure modes when ledgers are incompatible.

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 compact sentence that front-loads the action and immediately qualifies it with the non-blending guarantee. No filler, though the phrasing is dense enough that it reads slightly like jargon.

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 closed-world/read-only profile is covered by annotations. The description is adequate for a one-parameter comparison tool, with the only real gap being ledger input structure.

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 0% and the single parameter is an untyped array of objects with minItems 2. The description compensates only partially: it clarifies the items are 'tradition ledgers' supplied explicitly, but gives no hint about ledger structure, required fields, or why minItems is 2.

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 (compares) and resource (explicitly supplied tradition ledgers), and adds a distinguishing property: it preserves separation rather than blending. It does not name the nearest sibling (compare_conventions, compare_reading_versions), so an agent must still infer which comparison tool applies.

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 and no mention of alternatives among the many compare_* siblings. The phrase 'explicitly supplied' hints that inputs must be provided rather than fetched, but this is a constraint, not 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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the run is deterministic, never invokes another AI model, performs a fixed full-domain screen, checks contradictions and reports coverage. It does not describe latency, output size, or what happens if inputs are inconsistent (e.g., place vs lat/long).

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 routing claim in caps so the primary-vs-specialist decision is immediate. The middle sentence is a long run-on domain list, but each remaining sentence (extra depth, specialist routing, determinism) carries distinct information rather than restating the schema.

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 and coverage reporting need not be restated. However, for an 18-parameter tool with a nested consent object and low schema coverage, the description should at least say when profileRef and readingMode matter and what the consent block gates — it currently leaves 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 only 22% across 18 parameters with a nested remedyPreferences object, and the description explains none of them: no mention of how focus, question, detail, language, readingMode, traditions, asOfDate, or the remedyPreferences consent block interact. It does not compensate for the large under-documented surface, leaving the agent to infer how a 'normal question' maps onto focus vs question vs readingMode.

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 scope for a specific resource: a complete person-first Jyotisha screen across named life domains plus targeted Varga/timing depth on the exact question. It explicitly positions itself against siblings ('PRIMARY TOOL... use specialist tools only when...'), so an agent can tell it apart from analyze_chart_topic or get_depth_analysis without opening a 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 gives a clear when-to-use rule ('EVERY NORMAL USER QUESTION AND FIRST READING') and an explicit when-to-use-something-else rule ('use specialist tools only when this result requests additional inputs or the user asks for technical matrices'). The user-question vs technical-matrix split is a concrete routing 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one piece of interpretive context—that discovered prose is not to be treated as executable doctrine—but omits anything about the review-status semantics it reportedly returns. With annotations carrying the burden, this is an adequate 3.

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 tightly written sentence with the return content front-loaded. Dense but no filler; slightly jargon-heavy wording ('executable doctrine') is the only cost.

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 return values need not be re-explained, and annotations cover the safety profile. Still, the sole parameter is undocumented and no usage context is given, leaving the definition minimally sufficient for a retrieval/explanation 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 0% and the description does not explain what 'topic' means, what form it takes, or how it maps to a chart. With a single undocumented required parameter, the description should compensate but does not.

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 what it returns (book-section locators and rule-review status) tied to a chart topic, which is a specific output. However, it does not clearly distinguish itself from siblings like search_reviewed_rules, search_source_passages, or explore_lal_kitab_sources, leaving the agent unsure when this explanation tool is the right one. The trailing phrase about 'executable doctrine' is a caveat rather than a purpose statement.

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 named alternatives, despite several sibling tools that also retrieve sources and reviewed rules. The agent must infer the selection criteria 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 cover readOnly, idempotent, non-destructive, and closed-world behavior. The description adds meaningful context by disclosing the exact metadata classes returned and by explicitly stating that source body text is not republished, though it does not discuss auth, rate limits, or output shape beyond the field list.

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, front-loaded with the return content, no filler. Every clause earns its place by naming returned metadata or the body-text restriction.

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 has no parameters and an output schema exists, so return structure need not be explained. The description still provides enough scope (what metadata is exposed) and a key limitation (no body text), making it complete 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?

With zero input parameters, the 0-param baseline is 4. The schema has no parameters to document, and the description correctly does not invent any.

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?

Names a specific verb ('Returns') and enumerates the resource set: source families, locators, coverage counts, lexical risk signals, and disclosure policy. This is clear, but it never explicitly distinguishes itself from siblings such as analyze_lal_kitab or search_source_passages, so it falls 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?

The phrase 'without republishing source body text' implies a boundary (use this for coverage metadata, not for retrieving passages), but the description never states when to choose this over sibling tools or names an alternative. Usage is therefore only inferable.

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, openWorldHint=false, so safety and determinism are covered structurally. The description usefully adds that output is interpretive 'windows' rather than a deterministic prediction, which shapes how an agent should present results, but it says nothing about computational cost, required chart inputs, or failure modes when birth data is inconsistent.

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, zero filler, with the operative technique front-loaded and the interpretive caveat second. Nothing could be cut without losing 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-value shape needn't be described. However, for a 10-parameter tool with 0% schema coverage and no usage guidance, the description leaves significant gaps around required birth data, the location input branch, and the time-horizon parameter.

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 0% across 10 parameters, so the description carries the full explanatory burden and does not compensate. It never clarifies birth-data fields (name/date/time/place), the place-vs-latitude/longitude/timezone anyOf branch, the horizon control 'years' (0.25–20, default 5), or 'startDate'/'timezoneOffset'.

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 verb (finds overlaps) plus the exact astrological technique (Jupiter transiting the natal seventh sign intersected with Venus/seventh-lord Vimshottari periods). That technique-level specificity cleanly separates it from siblings such as analyze_marriage_structure, get_marriage_readiness, or find_muhurta, so an agent can route to it without opening schemas.

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 second sentence is a scope/liability caveat ('returns planning windows, never a guaranteed marriage prediction'), not usage guidance. There is no statement of when to prefer this over get_marriage_readiness, analyze_marriage_structure, or fuse_timing, and no prerequisites such as requiring an already-computed natal chart.

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 a closed-world scope, so safety is covered. The description adds that every pass/fail reason and a draft source key are returned, which is useful behavioral context, but says nothing about cost, computation intensity, or limits inherent to ranking many windows.

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 operation and the ranking factors with no filler. It is efficient, though the factor list is long enough that a reader must parse carefully.

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, but for a 10-parameter tool with a nested natal object and an anyOf location constraint, the description leaves parameter and prerequisite handling entirely to the schema, which itself only covers 30% of 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 only 30% across 10 parameters including a nested natal object, so the description is expected to compensate but does not. It implies a bounded date range and that Tara/Chandra Bala are optional (natal-dependent), but explains none of place/latitude/longitude/timezone alternatives, timezoneOffset, limit, or natal requirements.

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 (ranks candidate Muhurta windows) plus the bounded date-range scope and the factor set used for ranking. It is distinct from siblings like analyze_chart_topic, but it never names or contrasts the very close siblings find_muhurta_with_natal_fit and find_marriage_windows, so an agent cannot fully disambiguate 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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named despite two obvious overlapping siblings (find_muhurta_with_natal_fit, find_marriage_windows). Usage can only be inferred from the described computation.

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 the seven-day cap and the medical exclusion, which is useful scoping context, but says nothing about output shape, ranking criteria weighting, or why a window might be rejected.

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 with no filler, and the ranking scope is front-loaded ahead of the exclusion. Slightly under-specified rather than padded, which is preferable to 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 values need not be explained, and the annotations carry the safety profile. But for a 10-parameter tool with nested objects, a 30% schema coverage rate, and a required natal chart plus location duality, the description leaves too much of the invocation contract undocumented.

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 30% across 10 parameters, including a nested natal object with its own anyOf location requirement, so the description must compensate and it does not. None of activity, startDate/endDate, limit, or the place/coordinates duality is explained in the text.

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 (Ranks) and a bounded resource (a maximum seven-day range) and names the techniques applied (Panchanga, prohibited intervals, Tara Bala, Chandra Bala). It does not explicitly contrast itself with the sibling find_muhurta, so the 'natal fit' distinction is left to the tool 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?

The exclusion 'Medical procedures are unsupported' is a genuine when-not constraint, reinforced by the activity enum lacking a medical option. However, there is no guidance on when to pick this over find_muhurta or find_marriage_windows, so selection between near-identical siblings 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 establish a safe, idempotent read operation. The description adds useful behavioral context: natal promise acts as a hard gate, and returned windows are uncalibrated, auditable, and carry learnable factor weights. It does not cover auth or rate limits, but with annotations covering safety it clears the bar.

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 that states gating and output in 19 words. It is efficient, though its extreme brevity contributes to the missing usage and parameter detail rather than being merely concise.

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?

Even with an output schema covering return values and annotations covering safety, the definition is incomplete for an 11-parameter fusion tool. It lacks usage guidance and parameter semantics, so an agent cannot confidently select or invoke it from the description alone.

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 27% across 11 parameters, and the description provides no parameter information at all. It does not clarify date/time formats, the topic enum, startIso/endIso semantics, or the place vs. coordinates fallback, leaving much of the input contract undocumented.

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: applies natal promise as a hard gate and returns timing windows. It names the fusion of timing systems (title) and output type, but does not explicitly distinguish itself from siblings like analyze_transit_activation or find_marriage_windows.

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 no when-to-use guidance or alternatives. The hard-gate phrasing implies a precondition (natal promise), but there is no explicit direction on when to choose this fused timing tool over discrete transit, dasha, or muhurta 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds useful output-side context — the report spans Vargas, Yogas, current Dasha and upcoming Antardashas, and interpretations are 'qualified and evidence-linked' — but says nothing about generation cost, latency, or how the current-timing section depends on asOfDate/horizonYears.

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 verb and purpose are front-loaded, but the 18-item topic run-on bloats a single sentence and largely restates what the report covers rather than adding selection guidance. It is dense without being well-structured for an agent choosing between tools.

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 safety. However, for a 13-parameter tool with 7 required birth-data fields and near-zero schema descriptions, the definition leaves the agent without input guidance and without routing advice against the large sibling set.

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 13 parameters and only 8% schema description coverage, the description carries the burden of explaining inputs, yet it names none of them. The enumerated life areas loosely correspond to some focus enum values (career, marriage, education, property, health, spirituality), but nothing explains focus, language, horizonYears, asOfDate, or birthTimeAccuracyMinutes.

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 ('Builds') and a well-defined resource ('normal-person South Indian astrology report'), then enumerates the coverage so an agent can see it is broader than the narrow analyze_* siblings. It never names an alternative such as get_full_life_report_section or generate_report_pdf, so sibling differentiation is implied by breadth 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?

The exhaustive topic list implies this is the comprehensive, one-shot report generator rather than a per-topic analyze_* call, but there is no explicit when-to-use / when-not-to-use statement and no comparison with get_full_life_report_section or generate_report_pdf. Usage must be inferred from the sibling names.

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 declare a non-read-only, non-idempotent operation, so the agent knows calling twice yields distinct results. The description adds genuinely useful context beyond annotations by disclosing the artifact is server-side and the returned URL expires in 30 days. It does not explain what is consumed or created server-side, so it only partially extends the annotation picture.

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 covering the action, the artifact, and the return lifecycle. Nothing 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-value detail is not needed, and annotations cover the mutation profile. But for a 10-parameter tool with zero schema descriptions and no usage routing, the description is substantially 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?

With 10 parameters at 0% schema description coverage, the description carries the full burden and fails: it explains nothing about name/date/time, the place-vs-latitude/longitude/timezone alternatives, or asOfDate/horizonYears. The schema's anyOf structure encodes the branching, but no parameter's meaning or format is clarified.

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 (Generates), a concrete artifact (server-side PDF), and the delivery mechanism (hosted URL). An agent can distinguish this from render_chart or audit tools, though it does not explicitly contrast with siblings like generate_full_life_report.

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 indication of when to use this versus generate_full_life_report, get_depth_analysis, or render_chart, and no prerequisites given. The agent must infer usage from the name alone.

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 only a content inventory and no behavioral context (prerequisites, cost, why results differ from siblings). Given annotations carry the main burden, 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?

A single dense sentence with no filler, front-loading the returned artifacts. It is jargon-heavy but structurally efficient.

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 needn't be explained, and annotations cover safety. But for a 9-parameter composite tool with low schema coverage and zero usage guidance, the description is thin relative to the complexity it wraps.

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 9 parameters, so the description must compensate and largely does not. It only loosely implies a topic input via 'topic-specific' and offers no guidance on place vs latitude/longitude/timezone alternatives or date/time formats.

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 verb and enumerates concrete outputs (Vimsopaka, Ishta/Kashta, cross-Varga synthesis, special Lagnas, Yoga candidates, additional-Dasha status), so the agent knows exactly what content comes back. However, it never differentiates itself from close siblings such as analyze_varga or calculate_strength_profile, which overlap on the same artifacts.

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, when-not-to-use, or alternative-tool guidance at all. With ~40 siblings including analyze_varga and analyze_yogas, the agent has no signal for preferring this composite tool over the narrower specialists.

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