bva-corpus

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

Annotations already declare readOnlyHint and idempotentHint; the description adds meaningful context about being educational, that lists are representative, and what return information includes, exceeding annotation coverage.

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 paragraph of four sentences, front-loaded with main purpose, no waste, each sentence adds value.

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

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

Given the schema, annotations, output schema, and sibling tools, the description fully covers the tool's behavior, limitations, and usage context.

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

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

Schema description coverage is 100%, so the parameter descriptions are already clear. The tool description doesn't add significant new meaning beyond the schema's parameter descriptions.

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

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

The description clearly states the tool checks if a condition is a presumptive service connection, specifies covered exposure categories, and distinguishes it from sibling tools like list_conditions or search_bva_decisions.

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

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

The description explains when to use the tool (for presumptive conditions) and covers the scope, but does not explicitly state when not to use or name specific alternatives, though siblings imply context.

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?

Beyond annotations (readOnlyHint, idempotentHint), the description adds that ratings do not add linearly, supports bilateral factor, returns step-by-step breakdown, and is a deterministic estimate. This provides useful behavioral context without contradicting annotations.

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

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

The description is 3 sentences, front-loaded with purpose, then key behaviors, then disclaimer. Every sentence adds value with no wasted words.

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

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

Given the tool's complexity, the description covers the algorithm, official reference, bilateral factor, output structure, and deterministic nature. An output schema exists, so return values are handled. Minor omission: max items limit is in schema but not in description.

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 input schema is fully documented with descriptions for percent, label, and bilateral. The description adds context about the formula and rounding but does not add significant parameter-specific meaning beyond the schema. Baseline 3 is appropriate given high schema coverage.

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

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

The description clearly states the tool calculates a veteran's VA combined disability rating from individual ratings using the official formula. It specifies the verb 'calculate' and resource 'combined rating' and distinguishes itself from siblings which are about conditions, appeals, or reps, with no similar calculation tool.

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

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

The description implies usage for combining disability ratings with examples and formula details. It does not explicitly state when not to use or name alternatives, but given no similar siblings, the context is clear.

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 mark the tool as readOnly and idempotent, lowering the burden. The description adds meaningful behavioral context beyond that: it produces educational content, tailors a suggested starting point conditionally, and explicitly disclaims legal advice. This is useful and non-contradictory.

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 compact and information-dense, front-loading the core purpose before enumerating specific return content. Every clause earns its place: lanes, dockets, decision factors, tailoring behavior, and the educational disclaimer. It is organized for quick parsing by an agent.

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

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

With no required parameters, a fully documented schema, and an output schema present, the description covers all necessary context for correct invocation. It explains what the tool returns, when it is appropriate, and the optional tailoring behavior. No critical operational gaps remain.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining that wants_hearing and has_new_evidence influence a tailored suggested starting point, which goes beyond the raw schema field names. The third parameter, eligible_review_context_confirmed, is left to the schema, but the schema describes it thoroughly.

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 the specific verb 'Explain' with a precise resource: a veteran's options after a VA decision under the AMA. It lists the concrete content covered (three review lanes, three Board dockets, evidence rules, deadlines, best-fit guidance), which distinguishes it clearly from sibling tools like search_bva_decisions or get_claim_process.

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 establishes clear context: this is for explaining appeal options after a VA decision under the AMA, and it explicitly notes the tool is educational only and not legal advice. It does not explicitly name sibling alternatives or exclusions, but the context is specific enough for an agent to select it appropriately among the listed 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?

The description discloses key behavioral traits: it leads with free options, filters by multiple criteria, and mentions fee regulations for attorneys/agents. This adds value beyond the annotations (readOnlyHint, idempotentHint) by explaining the ordering and legal constraints. No contradiction with annotations.

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

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

The description is concise with three sentences: the first states the purpose, the second explains representative types, and the third adds legal context. It is front-loaded with the main action and avoids unnecessary details.

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 description is fairly complete for a read-only lookup tool. It covers purpose, filters, fee rules, and a disclaimer. The presence of an output schema reduces the need to describe return values. However, the inconsistency about 'language' filtering is a minor gap.

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

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

The description adds meaning by explaining the rep_type enum values and the fee implications for attorneys/agents. However, it mentions filtering by 'language' which is not a parameter in the input schema, causing confusion. Schema coverage is low (25%), so the description should compensate more fully, but it does not fully clarify all parameters (e.g., 'limit' is not explained).

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

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

The description clearly states the tool's purpose: finding a VA-accredited representative for disability claims or appeals. It specifies the verb 'Find' and the resource 'representative', and distinguishes itself from sibling tools like 'check_presumptive_conditions' by focusing on locating a human representative. The mention of filtering by state, city, type, and language further clarifies the scope.

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

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

The description provides context on when to use this tool: when one needs accredited representation for a claim or appeal. It explains the types of representatives and that free options are shown first. While it doesn't explicitly state when not to use it or contrast with siblings, the context is sufficient for typical use cases.

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?

Beyond the readOnlyHint/idempotentHint annotations, the description discloses several behavioral specifics: name/slug/alias resolution, a 50-decision-per-condition inspection cap, optional decision-level filtering, non-representative results, withheld grant rates, and the need to verify each issue against the original decision. No statement contradicts 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?

Each sentence adds distinct information: core operation, resolution and filtering behavior, then the limitations and verification caveats. The material is dense but front-loaded and contains no filler or restatement of 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?

For a tool with an output schema and read-only annotations, the description covers the operation, algorithm, limitations, and safety caveats well. It is slightly incomplete in not providing parameter-level detail for four optional filters and in not routing to sibling tools, but the enums and output schema reduce the impact of those omissions.

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

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

Schema description coverage is only 20%; the description compensates for the conditions parameter by explaining canonical names, slugs, aliases, and the per-condition inspection window. However, it only collectively calls the remaining parameters 'optional decision-level filters' and does not explain is_pact_act, sample_limit, exposure_basis, or service_connection_theory individually, leaving the enums to inference.

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

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

The description clearly states the operation (find source-linked recent Board decisions mentioning canonical conditions) and the resource/scope, so an agent understands the tool's core purpose. It does not explicitly name or contrast sibling tools such as search_bva_decisions or get_condition_report, so the differentiation is implied 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 description gives explicit negative guidance: results are research examples, not a representative sample, complete filtered cohort, outcomes, or chances of winning, and grant rates are withheld. It lacks an explicit 'use X instead' routing to sibling tools, but the boundary of appropriate use is clear.

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 indicate readOnlyHint=true and idempotentHint=true, so the tool is safe and idempotent. The description adds behavioral context: it is educational only, not legal advice, and provides overviews and deep dives with typical durations, tips, and do/don't guidance, which aligns with 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 description is a single, well-structured paragraph that front-loads the purpose ('Plain-English guide to the 8 stages'), then explains usage patterns, and ends with a disclaimer. Every sentence is necessary; no wasted words.

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

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

Given the tool's simplicity (one optional parameter, read-only, idempotent, with output schema), the description covers the tool's purpose, usage, behavior, and limitations comprehensively. It includes educational-only disclaimer, satisfying 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?

Schema coverage is 100%, with the parameter 'stage' having a description in the schema. The description adds meaning beyond the schema by explaining that omitting the parameter gives an overview and providing a stage number (1-8) gives a deep dive, including what to expect.

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

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

The description clearly states it provides a 'Plain-English guide to the 8 stages of a VA disability claim', using specific verbs ('guide') and resources ('8 stages'). It distinguishes from sibling tools (e.g., 'check_presumptive_conditions', 'estimate_combined_rating') by focusing on process overview and deep dives.

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

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

The description explicitly states when to use: 'whenever a veteran asks what happens after filing, where they are in the process, what a C&P exam is, or what to do at their current stage.' It also differentiates between calling with no arguments (overview) or with a stage number (deep dive). No explicit when-not-to-use, but the context is clear.

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 and idempotentHint, and the description adds substantial behavioral context beyond those: the report is corpus-grounded, includes a decision-level attribution limitation, withholds unverified extracted ratings, is educational (not prediction or legal advice), and may include source-cited summaries. These are valuable disclosures that help an agent set user expectations and understand limitations. No contradiction with annotations.

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

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

The description is dense yet efficient, packing a high amount of meaningful information into a compact structure. It front-loads the core action and result, then enumerates contents and caveats. Every clause adds value: scoping, content list, limitation, withheld data, source-cited summary, and the educational/prediction caveat. No redundant or filler words.

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

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

An output schema exists, so the description does not need to detail return fields. It covers the tool's purpose, content, limitations, and usage context well. The only notable gap is that example_limit is not explained anywhere, though it is optional with a default and the output schema may clarify its effect. For a complex report tool, the description is otherwise very complete.

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

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

Schema coverage is only 50% (condition has a description, example_limit does not). The description repeats the condition parameter's slug/alias semantics but adds nothing new for either parameter. Crucially, it does not explain what example_limit controls (e.g., number of examples or case listings), leaving a gap that the schema also fails to fill. Since coverage is low, 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 a specific verb and resource: 'return a full corpus-grounded report' for a single condition. It enumerates the report's components (outcomes, theory labels, attribution limitation, withheld ratings, source-cited summary) and explicitly differentiates from siblings by calling itself 'The richest single call for "tell me about VA claims for <condition>"'. This leaves no ambiguity about what the tool does or how it differs from sibling 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?

The description gives a clear usage context ('The richest single call for ...') which implies using this tool when a comprehensive condition overview is needed. However, it does not explicitly name alternative tools or state when not to use it, e.g., for searching individual decisions. This falls just short of explicit when/when-not guidance, but the context is clear enough for an agent to infer appropriate use.

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

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

Annotations already provide readOnlyHint=true and idempotentHint=true. The description adds context that counts reflect only quality-filtered, publicly visible decisions, which is a useful behavioral nuance beyond annotations.

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

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

Three concise sentences. The first lists return values, the second provides usage guidance, the third adds a qualifier. No wasted words, all information is relevant and front-loaded.

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

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

The description fully covers the tool's purpose and output for a zero-parameter tool. It lists all returned statistics and adds a qualifier about data filtering. With an output schema expected, the description is complete.

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

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

There are zero parameters, so the baseline is 4. The description does not need to add parameter information; it appropriately focuses on the output and usage.

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

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

The description clearly states the tool returns live corpus statistics and lists specific data points (number of decisions, outcome distribution, date range, accredited representatives). It distinguishes itself from siblings by providing a general overview rather than specific case processing.

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

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

The description explicitly says when to use: 'to establish the scale of the data behind an answer, or when someone asks how much data do you have / how current is it.' It does not mention when not to use or alternatives, but sibling context makes differentiation clear.

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 and idempotentHint, but the description adds crucial behavioral nuance: counts represent whole decisions, not condition-specific wins, and counts reflect only quality-filtered, publicly visible decisions. This goes beyond the annotations and clarifies data semantics.

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

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

The description is well-structured: main purpose in the first sentence, followed by usage guidance, then important caveats about count semantics and filtering. Every sentence adds value, and the length is appropriate for the tool's complexity.

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

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

Given the tool has no parameters and an output schema exists (signaled), the description covers all necessary context: what data is returned, the key caveat about counts, and how it relates to get_condition_report. Nothing essential is missing 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 parameters, the baseline is 4. The description doesn't need to explain parameters, but it does describe the output fields (counts, grants, remands, body-system category), which aids the agent even though no inputs are required.

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 ('List') and names the exact resource: standardized conditions with counts and body-system categories. It clearly states what the tool does and implicitly differentiates itself from the sibling get_condition_report, making it easy for an agent to understand its role.

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

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

Explicitly states when to use the tool: 'discover which conditions have data, to get the exact slug for get_condition_report, or to see which conditions occur in this collection.' This provides clear context and references the alternative tool, leaving no ambiguity about selection.

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 and idempotentHint=true, establishing the safety profile. The description adds that results are 'vetted decisions with a plain-English summary, the deciding factor, and a link', adding context beyond annotations but not contradicting them.

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 two concise sentences, front-loading the action ('Search real...') and listing filters efficiently. Every phrase adds value with no redundancy.

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 complexity (9 parameters, 22% schema coverage), the description outlines the key return fields (summary, factor, link) and the presence of an output schema reduces burden. However, it omits important behavioral details like pagination or result limits beyond the limit 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 only 22%, and the description does not add detailed parameter semantics beyond listing filter categories (e.g., 'keyword, claimed condition, disposition'). For the many parameters without schema descriptions, the description offers no additional guidance on format, syntax, 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 clearly states the tool searches real U.S. BVA decisions by multiple criteria and lists specific filters. It distinguishes from sibling tools like find_similar_appeals or get_corpus_stats by focusing on searching actual decisions.

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

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

The description explicitly says 'Use to ground any claim about how VA appeals have actually been decided.' This provides clear context for when to use the tool, though it doesn't explicitly mention when not to use it or compare to alternative tools.

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