CompatAir

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is clear. The description adds the behavioral note that missing component data remains explicit, which is useful but not extensive.

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 very concise at two sentences with no fluff. However, it sacrifices informativeness for brevity, leaving out important parameter 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?

Given the complexity of the tool (4 parameters, required toolIds, enum, limits), the description is insufficient. It does not explain the purpose of each parameter, the output format, or how components are combined, despite the presence of an output 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?

With no parameter descriptions in the schema (0% coverage) and no mention of parameters in the description, the agent receives no guidance on how toolIds, mode, limit, or compressorId affect the system building.

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 builds a complete air system with listed components, distinguishing it from sibling tools focused on comparison or search. However, it does not explicitly clarify that it is a read-only configuration tool, relying on annotations for that nuance.

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 guidance is provided on when to use this tool versus alternatives like compare_complete_systems or search_tools. There is no mention of prerequisites 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 declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds no behavioral detail beyond stating it compares and produces a normalized verdict. With annotations present, this is adequate but unremarkable.

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 sentence plus a legacy prefix. Every part earns its place; 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 three parameters, an output schema, and annotations, the description fails to explain what a 'normalized verdict' means, the role of safetyMargin, or any preconditions. The legacy warning is useful but insufficient for complete 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 coverage is 0%, so the description must compensate. It mentions 'compressor' and 'tool' but does not explicitly map to parameter names (compressorId, toolId, safetyMargin) or explain safetyMargin's purpose. This leaves significant gaps.

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 compares a compressor and a tool with a normalized verdict, and explicitly marks itself as legacy, distinguishing it from the preferred sibling evaluate_air_compatibility.

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 directly advises against using this tool, recommending evaluate_air_compatibility as the alternative. This provides explicit when-not-to-use guidance and an alternative.

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, so the tool is safe and non-destructive. The description adds value by specifying that comparisons are 'on documented technical facts without a commercial score,' which provides context beyond the annotations. No contradictions.

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, concise sentence that efficiently conveys the tool's purpose. However, it could benefit from slightly more detail about the comparison scope without losing conciseness.

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

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

Given the tool's moderate complexity (comparison of 2-5 systems on technical facts) and the presence of an output schema, the description provides minimal context. It leaves open questions about what 'documented technical facts' means and the comparison format. It is adequate but not comprehensive.

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 coverage is 0%, meaning the description does not explain the 'systems' parameter. While the schema defines the parameter structure well, the description lacks any detail about how to use the parameter or what data is expected. This does not compensate for the lack of schema documentation.

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: comparing two to five complete configurations on documented technical facts without a commercial score. It uses a specific verb ('compare') and resource ('complete configurations'), and distinguishes from siblings like 'compare_compressors' or 'evaluate_air_compatibility'.

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 indicates usage for comparing configurations on technical facts, but does not explicitly state when to use this tool versus alternatives or provide contextual guidelines. Sibling tools exist (e.g., 'compare_compressors'), but no differentiation is given.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering safety. The description adds that the tool is legacy and compares without commercial score, which is relevant behavioral context not in 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 extremely concise with one sentence and a legacy warning, no wasted words. Key information is front-loaded.

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

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

Given the tool's simplicity (one parameter, output schema exists, annotations rich), the description is nearly sufficient. It covers legacy status and scope. However, it lacks explanation of output or what 'commercial score' means, but output schema likely covers return values.

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%, so the description must compensate. It mentions 'deux ou trois' which aligns with minItems/maxItems, but does not explain what the 'ids' represent (e.g., product IDs). The description adds minimal 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 clearly states 'Comparer deux ou trois compresseurs sans score commercial' which is a specific verb and resource, and it distinguishes from sibling 'compare_complete_systems' by marking itself as legacy. However, the description is in French, which may reduce clarity for an English-preferring agent.

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

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

Explicitly says 'LEGACY : préférer compare_complete_systems' and states the scope ('deux ou trois compresseurs') and constraint ('sans score commercial'), providing clear guidance on when to use and when to avoid.

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. The description adds the constraint that it never accepts sensitive data, which is useful but minimal. No contradictions 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?

Two sentences with no wasted words. The key purpose is front-loaded. However, the conciseness sacrifices completeness, as there is room to add critical parameter context without becoming verbose.

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 (6 parameters, nested schemas, many siblings, output schema exists), the description is severely incomplete. It fails to mention the intent field, constraints, or output options, leaving the agent without sufficient context to invoke 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 0%, placing the burden on the description to explain parameters. The description only vaguely references 'compressor' and 'tools' from the configuration object, ignoring all other parameters (meta, ucp, intent, constraints, requested_outputs) and their 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 description states a specific verb ('compatibility decision') and resource ('one documented compressor and one or more pneumatic tools'), clearly indicating the tool's function. However, it does not differentiate from sibling tools like 'check_compatibility' or 'explain_compatibility_verdict', which share similar purposes.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. While it mentions it is read-only and excludes certain data types, it lacks context for selecting among the many sibling tools (e.g., compare_compressors, find_compatible_alternatives).

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. The description adds value by specifying the factors explained (pressure, flow, duty-cycle, missing-data), providing behavioral 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?

A single, front-loaded sentence that conveys the tool's purpose without unnecessary words or repetition. Every word earns its place.

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

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

With an output schema present, description need not explain return values. However, missing parameter semantics and usage guidelines make the tool less complete. Adequate but with clear gaps.

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 provides no meaning for the two required parameters (toolId, compressorId). It does not clarify what these identifiers represent, leaving the agent to guess.

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 action 'explain' and the resource 'compatibility verdict', specifying the exact factors covered (pressure, flow, duty-cycle, missing-data). It distinguishes from siblings like 'check_compatibility' and 'get_compatibility_evidence' by focusing on explanation after a verdict is published.

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 guidance on when to use this tool vs alternatives like 'check_compatibility' or 'evaluate_air_compatibility'. The description implies it is for explaining an already-published verdict but does not explicitly state prerequisites or when not to 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 indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context by stating it returns 'only documented' items, implying incomplete results if undocumented accessories exist. 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 very short (one sentence) and front-loaded with the legacy warning. However, it is in French, which may reduce accessibility for English-centric agents, but still earns its place.

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

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

For a simple tool with one parameter and an existing output schema, the description is largely complete. The legacy note and sibling reference provide context. Minor gap: no mention of what constitutes a 'tool' or how toolId is used.

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 only parameter 'toolId' has no description coverage (0%), and the tool description provides no additional meaning beyond the parameter name. The agent cannot infer expected format or constraints from 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?

The description clearly states the tool returns only documented fittings/accessories for a given tool, and explicitly marks it as legacy while directing to a sibling (build_complete_air_system). This provides a specific verb, resource, and scope, effectively distinguishing it from alternatives.

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 'LEGACY: prefer build_complete_air_system', giving direct guidance to avoid this tool in favor of a sibling. This is a clear when-to-use and when-not-to-use instruction.

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. The description adds one behavioral note ('Commercial commission never affects ordering') which is unique but not critical for understanding the tool's core behavior. No contradicting statements.

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 with no redundant words. Every clause contributes information. Front-loaded with the primary action and a clarifying note.

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

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

For a tool with no parameter descriptions, required parameters, and an output schema (unseen), the description fails to provide enough context about inputs, outputs, or edge cases. It does not compensate for missing schema descriptions.

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 0% schema description coverage and 4 parameters (2 required), the description fails to explain what compressorId or toolIds represent. 'compressor substitution' is vague, and the meaning of 'smallest' (size, cost, power?) is undefined. No parameter semantics are conveyed.

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 finds a verified compressor substitution for incompatible systems, with the specific qualifier 'smallest' and an unusual note about commission. It distinguishes well from siblings focused on building, comparing, or checking compatibility.

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 the tool is for finding alternatives when a system is incompatible, but does not explicitly state when to use this tool versus alternatives like search_compressors or evaluate_air_compatibility. No usage or exclusion guidance beyond the core purpose.

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. The description adds context about returning 'active offers from authorized streams', which provides behavioral nuance beyond annotations. No contradictions.

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 short sentence with a legacy prefix, making it concise and front-loaded. However, use of French may require agent translation, slightly reducing efficiency.

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 3 parameters and an output schema, the description lacks essential context such as the meaning of 'active', 'authorized streams', and how parameters affect results. It is incomplete for proper agent 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%, and the description provides no information about any of the three parameters (limit, cursor, productId). This is a critical gap, as agents cannot infer how parameters control filtering or pagination.

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 active offers from authorized streams, and explicitly labels it as LEGACY with a preference for get_current_offers. This distinguishes it from siblings, though the French wording may slightly reduce clarity for non-French agents.

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 'préférer get_current_offers' (prefer get_current_offers), giving direct guidance on when to avoid this tool in favor of an alternative. This is excellent usage guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds context on the type of changes returned (catalog, method, offer snapshot), which goes 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?

Single sentence with 14 words, front-loaded with verb and resource, no waste.

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

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

Output schema covers return values, but description omits pagination details (cursor, limit) which are important for changefeed usage.

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 description only explains the 'since' parameter, leaving 'limit' and 'cursor' undocumented. Description must compensate but doesn't fully cover all 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?

The description clearly states the tool returns catalog, method, and offer snapshot changes since a date/version. It distinguishes from sibling tools like 'get_current_offers' which return current snapshots, not changes.

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 use for retrieving changes since a point, but lacks explicit guidance on when not to use it or alternatives among many sibling retrieval tools.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by specifying the exact content returned (evidence, URLs, edges) and that it is scoped to 'one compatibility result'. No contradictions.

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?

Single, short sentence (16 words) that starts with the verb 'Return'. No redundant 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 available, the description need not detail return values. However, it lacks context about prerequisites (e.g., must have previously called a compatibility-checking tool) and that it retrieves data for a specific result identified by the two 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 0%, so the description must compensate. However, it does not mention the parameters ('toolId', 'compressorId') or clarify that they together identify the compatibility result. The agent may not understand that both are required and what they represent.

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 specifies a concrete action ('Return') and a clear resource ('characteristics, evidence references, source URLs and AirGraph edges used for one compatibility result'). It distinguishes from siblings like 'check_compatibility' (which likely determines compatibility) and 'explain_compatibility_verdict' (which explains the verdict). However, it could more explicitly state that it returns the underlying evidence for a specific result.

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 guidance on when to use this tool vs alternatives like 'check_compatibility' or 'explain_compatibility_verdict'. The description implies it is used after compatibility is determined, but this is not stated explicitly.

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, which the description does not contradict. The description adds 'characteristics and sources' but no further behavioral details (e.g., data source freshness, authorization).

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 sentence with a legacy warning front-loaded, making it concise and scannable. It could add a parameter hint without much bloat, but overall it is 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?

Despite an output schema existing, the description omits critical input semantics (the 'id' parameter) and does not specify what 'characteristics' or 'sources' entail. For a legacy tool with a clear alternative, the documentation is incomplete for reliable 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 0% schema description coverage, the description fails to clarify what the single 'id' parameter represents (e.g., compressor model ID, part number). The agent has no guidance on parameter values beyond the type 'string'.

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

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

The description clearly states the tool returns compressor characteristics and sources, explicitly marks itself as legacy and recommends identify_product instead, providing specific verb+resource and sibling differentiation.

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 advises preferring identify_product, giving clear context on when not to use this tool. However, it does not elaborate on edge cases or alternatives beyond that single sibling.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by explaining the tool separates pricing from technical verdicts and returns only fresh allowlisted data, providing 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?

The description is two sentences long, concise, and front-loaded with the primary action. Every sentence adds meaningful information without 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?

While the description covers the core purpose and constraints, it omits pagination behavior (cursor/limit) and response structure, despite having an output schema. Additional context on how to use these parameters would improve 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?

With schema description coverage at 0%, the description must explain parameter meanings but does not mention any parameters (limit, cursor, productIds). The agent must infer their roles from context, which is insufficient.

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 'dated current prices and availability separately from technical verdicts,' specifying the resource and scope. It also notes that only 'allowlisted, fresh merchant destinations' are returned, providing a distinct purpose that differentiates it from siblings like 'find_offers'.

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 use when needing current pricing and availability without technical verdicts, and mentions constraints (allowlisted, fresh merchants). However, no explicit when-not to use or alternatives are given, leaving some ambiguity.

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. The description adds that it returns 'published requirements', which is a mild behavioral detail. It does not contradict 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 very concise with two meaningful parts: the legacy note and the purpose. It is front-loaded and efficient, though it omits parameter 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?

Given the tool has only one required parameter and an output schema, the description is minimally complete. It covers the purpose and legacy status but does not explain the parameter or the return value beyond 'exigences publiées'.

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 provides no information about the 'id' parameter (e.g., what kind of ID, format, or meaning). The description fails to add any value beyond the schema's type definition.

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 'Retourner les exigences publiées d'un outil' (Return the published requirements of a tool) with a specific verb and resource. The legacy note explicitly distinguishes from sibling 'identify_product' by advising to prefer it.

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 'LEGACY : préférer identify_product', providing clear guidance on when not to use this tool and which alternative to use. However, it does not specify any scenario where this tool should be used instead.

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 readOnly, idempotent, and not destructive. The description adds 'No network fetch is performed,' which is a useful behavioral trait. However, it does not mention what happens with no match or multiple matches, nor the effect of the limit 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?

The description is a single sentence, front-loaded with the main action. It is concise with no fluff, but could be slightly more structured by separating the identifier list or noting the 'query' parameter explicitly.

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 5 optional parameters and an existing output schema, the description covers the main inputs but lacks details on combining parameters, the purpose of 'limit,' and the return format (though output schema exists). It is adequate but not fully complete.

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

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

Schema coverage is 0%, so the description carries the burden. It maps identifiers (name, URL, EAN, etc.) to parameters (query, url, ean, reference) but omits the 'limit' parameter and does not clarify that 'query' handles names. This adds partial meaning but leaves gaps.

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 identifies a catalog product from various identifiers (name, URL, EAN, MPN, reference, CompatAir ID). It is specific about the verb and resource but does not differentiate from sibling tools like search_compressors or find_compatible_alternatives.

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 guidance on when to use this tool versus alternatives. The description only lists input types and notes no network fetch, but does not explain contexts where sibling tools are preferable or when not to use this 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 indicate read-only, idempotent, non-destructive; description adds no further 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?

Single sentence is concise and front-loads the legacy warning; no wasted text, though minimal.

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 6 parameters and an output schema, description is too sparse; lacks info on return values or typical usage.

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?

0% schema description coverage and no explanation of parameters (query, oilType, etc.) in description; fails to compensate.

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

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

Description clearly states it searches for compressors by technical criteria and labels itself as legacy, distinguishing from sibling identify_product.

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 advises against using this tool, preferring identify_product instead; clear when-not-to-use and alternative.

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. The description adds the critical behavioral guarantee that 'the server never fetches arbitrary external content', clarifying the scope of search and ensuring safety 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?

Two sentences front-loaded with purpose and a key behavioral guarantee. No unnecessary words; every 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?

With 5 parameters and no parameter descriptions, the description leaves significant gaps. While output schema may exist, missing usage guidelines and parameter semantics make it incomplete for an agent to use 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 0% and the description does not explain any of the 5 parameters (query, type, limit, cursor, locale). The agent has no semantic guidance for how to use parameters like the meaning of type enum values or pagination via cursor.

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

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

Description clearly states the tool searches published guides, glossary, methods, and product pages with the verb 'Search'. It lists specific content types, but does not explicitly differentiate from sibling tools like search_compressors or search_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?

No guidance on when to use this tool versus alternatives like search_compressors or compare tools. Does not mention when not to use or context where other tools are preferred.

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 readonly, idempotent, and non-destructive behavior. The description adds no further behavioral details beyond the legacy status, which is useful but minimal.

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 very short and to the point, but it lacks structure and could benefit from front-loading key information. The legacy note is helpful but the overall brevity sacrifices clarity.

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 four optional parameters and existing output schema, the description is incomplete. It provides no guidance on pagination, filtering, or parameter usage, leaving significant gaps for an agent.

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 has 0% description coverage and the description does not explain any of the four parameters, leaving the agent without guidance on how to use them effectively.

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: searching for documented pneumatic tools. The legacy note and reference to identify_product add context, but the core action and resource are unambiguous.

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

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

The description explicitly recommends using identify_product instead, providing clear guidance on when to avoid this tool. However, it does not specify any scenario where this tool should be used.

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, so the tool is safe and idempotent. The description adds the legacy status and the alternative tool, which is behavioral context beyond annotations. However, it does not describe return values, error behavior, or other runtime traits. With annotations covering safety, a score of 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?

The description is a single sentence plus a legacy tag, with no wasted words. The most critical information (legacy status and alternative) is front-loaded in brackets. The structure is optimal for quick agent interpretation.

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

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

The tool is complex with three demand types and multiple parameters. The description is minimal but adequate given the tool's legacy status and the existence of an output schema. It explains the high-level functionality but lacks details on parameter semantics. For a legacy tool, this is acceptable but not 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 0%, so the description must compensate. It mentions three demand types (continuous flow, per-action, inflation) which map to the model field's enums. This provides some context for the main 'demands' parameter. However, it does not explain 'mode', 'safetyMargin', 'measuredLeakLpm', or 'measuredPressureDropBar'. For a tool with 5 parameters, this is moderate help.

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: sizing a continuous flow, per-action need, or inflation. It also explicitly distinguishes from the sibling tool 'build_complete_air_system' by labeling itself as legacy and recommending that alternative, making the purpose and preference unambiguous.

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

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

The description provides explicit guidance: it is a legacy tool, and the agent should prefer 'build_complete_air_system'. This tells both when to use this tool (only for legacy needs) and when not to use it (when the newer tool is available). The specific alternatives are named.

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