CompShop

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

Annotations already establish the safe read-only, idempotent profile, so the bar is lower. The description adds real behavioral context beyond them: it discloses the hybrid literal + embedding matching strategy and the ranking behavior that demotes niche cuts behind broad-coverage surveys, which materially shapes result interpretation.

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 no filler, front-loaded on what the tool finds and immediately followed by the semantic-matching behavior and ranking rule. Every sentence carries information an agent needs.

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

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

With no output schema, the description usefully explains that results are ranked surveys with broad-coverage ones first, which compensates for the missing return documentation. It is largely complete for a two-parameter read tool, though it omits any hint of result count limits or empty-result behavior.

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 both the free-text 'position' input and the limit bounds (1-20, default 5) are already documented in structured fields. The description reinforces that abbreviations and paraphrases are fine for 'position' but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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

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

Names a specific verb and resource ('find compensation surveys') and scopes it to a job title, with concrete examples. It is clear what the tool does, but it never contrasts itself with the overlapping sibling recommend_surveys, so an agent cannot fully disambiguate from the description alone.

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

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

The description implies when to use it ('benchmark a specific job title or position') and notes that abbreviations and paraphrases are acceptable input. However, it gives no when-not guidance and does not name or defer to any alternative such as recommend_surveys, leaving the routing decision 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=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds no behavioral context beyond those hints - no indication of what 'detailed info' contains or that a missing slug yields an error.

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 short sentence with the resource and scoping key front-loaded and no filler. It is efficiently sized for a simple single-record fetch, though it is arguably too terse to be called maximally informative.

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

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

For a one-parameter read tool with rich annotations, the essentials are present, but there is no output schema and the description never says what a 'report' contains, so an agent cannot anticipate the return shape. Adequate but with a clear gap.

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

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

Schema description coverage is 100% and the single parameter even includes a concrete example slug, so the schema carries the full burden. The description's phrase 'by slug' merely restates the schema and adds no format or validation detail. Baseline 3 applies.

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

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

States a specific verb (get/retrieve) and resource (single survey report) plus a scoping key (by slug), which is enough for an agent to know exactly what comes back. It does not need heavy sibling differentiation here since the sibling names (vendors, surveys-for-position, search) are clearly distinct resources.

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 statement of when to use this versus find_surveys_for_position, recommend_surveys, or search, and no prerequisites beyond the implied need for a slug. The reader must infer that a slug has to be obtained elsewhere first.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds the useful fact that the response bundles all of the vendor's reports, but says nothing about response size, pagination, or auth requirements.

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 short sentences, front-loading the operation and its scope before the routing hint. No filler and nothing redundant.

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

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

There is no output schema, so the description correctly mentions what comes back ('all of their reports'), which is the key completeness item for a lookup tool. Minor gaps around response volume/error behavior keep it from a 5.

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

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

Schema description coverage is 100% and the slug parameter even carries example values ('mercer-benchmark-database', 'pas', 'wtw'). The description repeats only 'by slug' and adds no format or resolution rules beyond the schema, so the baseline 3 applies.

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

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

States a specific verb (get) and resource (vendor by slug) plus the return scope (all of their reports). This lets an agent distinguish it from the list_* siblings and from get_report without opening any schema.

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

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

Explicitly names the two preceding tools ('search' or 'list_vendors_by_industry') whose output feeds this one, giving clear call-order context. It does not state any when-not-to-use condition, so it falls short of a full 5.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only the word 'every', implying a complete unfiltered enumeration rather than pagination behavior; no additional behavioral context is offered.

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 short sentences, zero waste, with the what (list vendors by industry) front-loaded ahead of the usage cue. Nothing to trim.

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

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

For a single-parameter, closed-world read tool whose safety and idempotency are already captured by annotations, the description is sufficient; the return value ('every vendor') is implied and no output schema exists to require elaboration.

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% and the single enum parameter is fully documented in the schema itself, so the baseline is 3. The description restates the industry scoping but adds no syntax or format detail beyond what the enum already provides.

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 (List) plus resource (CompShop vendors that publish surveys) and the scoping dimension (industry), which cleanly separates it from list_vendors_by_region. An agent can tell instantly what this returns.

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?

Provides an explicit trigger phrase ('what survey publishers cover [industry]?'), giving clear context for invocation. It does not name alternatives such as list_vendors_by_region or recommend_surveys, so the when-not case is left implicit.

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

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

Annotations already declare this read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: region is matched against both vendor-level scope and individual report scopes, which explains how results are computed.

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, no filler, and the core purpose is front-loaded ahead of the usage trigger. Every clause 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 single-parameter read-only list tool with full enum documentation and no output schema, the description is nearly complete. It could say a word about what each vendor entry contains, but with readOnly hints and a trivial schema this 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?

Schema coverage is 100% and the enum is fully documented with all eight values, so the schema carries the parameter burden. The description still adds meaning by explaining the matching semantics of 'region' (vendor scope plus report scope), which the enum alone does not convey.

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 ('List') and resource ('vendors with survey coverage') qualified by region scope, which is more precise than the bare name. It does not explicitly name the sibling list_vendors_by_industry, so an agent must infer the region-vs-industry distinction rather than being routed to 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?

It gives an explicit trigger ('Use when the user asks what publishers cover [region]?'), which is clear context for when to reach for this tool. It stops short of stating when NOT to use it or naming the alternative sibling for a different facet (industry).

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

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

Annotations already establish readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds useful behavioral context beyond that by stating the output is 'ranked vendors with rationale,' but it says nothing about ranking methodology, limits on results, or how empty/marginal matches are handled.

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

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

Three short sentences, front-loaded with the purpose, then the trigger, then the output and parameter summary. It is tight and scannable. It loses a point only because the trailing required/optional sentence largely duplicates the schema rather than earning 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 four-parameter, read-only tool with no output schema, the definition covers purpose, trigger, output shape and parameter roles adequately. No output schema exists, so the description's note about ranked vendors with rationale fills the gap; only edge-case behavior and sibling disambiguation are missing.

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

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

Schema description coverage is 100% and both enums are fully enumerated in the schema, so the parameters are already self-documenting. The description's 'Required: industry. Optional: region, role focus.' merely restates the schema and adds no syntax, format, or selection guidance beyond it, matching the baseline 3.

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

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

The description gives a specific verb+resource: 'Recommend the best-fit compensation surveys given a hiring/benchmarking context,' and adds that it returns 'ranked vendors with rationale.' It is clear what the tool produces, but it never explicitly distinguishes itself from the close sibling find_surveys_for_position, which an agent could reasonably confuse it with.

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

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

It provides an explicit trigger: 'Use when the user asks what survey should I use for [situation]?' That is a concrete, quotable condition. However, it names no alternative tool or when-not-to-use condition, which matters given the overlapping find_surveys_for_position and list_vendors_by_industry 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds value by disclosing the return shape — grouped results across four entity types — which matters since there is no output schema. It omits grouping/pagination mechanics that the 'max results per group' limit implies, but this is a minor gap.

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

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

Three tight sentences with zero redundancy: purpose, return contents, and usage context, ordered from what-it-is to when-to-use. Nothing needs trimming.

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

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

With no output schema, the description appropriately describes what the four result categories are, and annotations carry the safety profile, so an agent has enough to call it correctly. Only the result grouping/ordering behavior implied by the per-group limit is left unstated.

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 both parameters are fully documented in the schema, including the limit default and cap. The description's parenthetical list of query facets (job title, industry, vendor, geography) merely echoes the schema's query description, adding no syntax or format guidance beyond it. Baseline 3 applies.

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

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

States a specific verb and resource — free-text search across the CompShop survey directory — and enumerates the result entity types (vendors, reports, job families, positions). It implicitly positions itself as the general discovery tool via 'open-ended discovery questions', but it never names the targeted siblings (find_surveys_for_position, get_vendor) that an agent must choose between.

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?

Clear usage context is given: use for open-ended discovery, with two concrete example queries ('biotech surveys in Europe', 'CEO compensation data'). No explicit when-not or named alternatives are provided, but the 'open-ended' framing implies the boundary against the structured lookup siblings.

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