Agency Standings

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

Annotations already declare readOnlyHint=true, destructiveHint=false and a closed world, so safety is covered. The description adds non-obvious behavioral context: the result is a full evidence review with provenance (URLs plus retrieval dates) and it explicitly states 'No numeric score', which warns the agent not to expect a rating field.

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

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

Front-loaded with the action and resource, then a compact enumeration of the return payload. The middle sentence about filtered searches is slightly oblique but earns its place by preventing confusion with search results. No filler.

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

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

With no output schema, the description carries the return-value burden, and it does so by listing the substantive fields including provenance data. It could go slightly further on error behavior for an unknown slug, but for a single-record read-only getter the essentials are covered.

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 both parameters documented, so the baseline is 3. The description reinforces that 'slug' selects exactly one agency, but it adds nothing about the optional user_request parameter or slug formatting beyond what the schema 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 and resource ('Return the full evidence review for one agency slug') and enumerates the payload: rank or unranked standing, services, sourced facts with URLs and retrieval dates, profile and contact URLs. The clause 'A filtered search can show a different position' implicitly separates it from the plural search_agencies sibling, so an agent can route correctly without opening a schema.

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

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

The description gives clear context for when this record is the right one to read: a single canonical agency lookup whose position may differ from a filtered search result. It stops short of naming search_agencies or stating an explicit exclusion, so the agent must infer the alternative rather than being told.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it discloses that the returned explanation includes rank numbers but not a numeric score, which is useful since no output schema exists. It still omits anything about permissions, rate limits, or freshness of the ranking rules.

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?

Four short sentences, front-loaded with the core purpose, so there is little wasted verbiage. The middle sentence ('Real rankings, earned through evidence: client results, testimonials and published work') leans promotional rather than functional, which keeps it from a 5.

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 zero-required-parameter read-only explainer with no output schema, the description covers purpose and the key content distinction (rank numbers present, numeric score absent). It could say more about what the explanation covers, but nothing critical to invoking the tool is missing.

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

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

Schema description coverage is 100% and the single optional user_request parameter is fully documented in the schema, so baseline is 3. The description adds nothing about the paraphrase parameter or its purpose.

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

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

The description names a specific verb and resource (explain the ranking methodology) that clearly separates it from siblings like get_agency, search_agencies, and search_work, which all deal with agency data rather than ranking rules. It falls short of a 5 only because the closing lines about rank numbers vs. numeric scores read as content claims rather than a crisp statement of what the tool 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?

Usage is only implied: an agent can infer this is the tool for questions about how rankings work, but the description never states when to call it versus get_started or get_agency, nor any exclusion or trigger phrasing. No alternative is named.

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

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

Annotations already establish this is a safe read-only, non-open-world call, so the bar is low. The description adds real behavioral context: it is a conversational disambiguation step that should ask the user a question, and it discloses a capability limit ('Qualified briefs are not open yet'). It stops short of stating what the call returns or that it stores nothing, but that gap is minor given 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?

Front-loaded with 'Start here' and then the two paths in order; every sentence carries routing or scope information and none is filler. It is slightly dense in the agency-path clause but still compact and readable.

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 router tool with one optional parameter, no nested objects, and no output schema, the description supplies what an agent needs: when to invoke it, the two branches, and the follow-up tool for each. It does not mention that the call returns no listing data itself, a minor omission only.

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 user_request parameter is fully described in the schema. The description implies capturing the user's intent but adds no syntax, length, or formatting meaning beyond it, so the 3 baseline 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?

The opening 'Start here' plus the two-path routing statement makes it unmistakable that this is the entry-point/disambiguation tool rather than a data fetcher. It explicitly names the sibling tools each path leads to (search tools, join_as_agency), so an agent can distinguish it from get_agency, search_agencies, and join_as_agency without opening a schema.

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

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

It gives an explicit branching condition: brand looking for an agency vs. agency wanting to join. Each branch names the concrete follow-up tools, and it adds an exclusion ('Qualified briefs are not open yet') so the agent knows not to attempt that path.

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 cover the safety profile (not read-only, not destructive, closed-world), and the description adds real context beyond them: the record is stored as 'pending', it is reviewed before listing/ranking, and ranking cannot be bought. It stops short of stating permissions, idempotency, or what happens on a duplicate submission.

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 first sentence and the field list are front-loaded and useful, but the three trailing sentences about evidence-based ranking are policy copy that does not help an agent invoke the tool correctly. The description also omits user_request while enumerating the other fields.

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 7 parameters, 6 required, no output schema, and no enums, the description covers most of the surface but never mentions the user_request field, and says nothing about the response or what a caller should do after a successful store. 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 coverage is 100%, so all seven parameters are already documented, including the 'no street address or phone number' constraint on location. The description restates the field list rather than adding format or syntax 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?

States a specific verb and resource: 'Store a pending agency application.' The 'pending' qualifier and the review framing distinguish it from read-only siblings like get_agency and search_agencies, so an agent knows this is the submission path.

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 clear context (a pending application subject to evidence review) and an explicit field-level exclusion: 'Do not collect a phone number or street address.' It does not name a sibling or state an explicit when-not beyond that, so it falls short of a 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=true, destructiveHint=false and a closed world, so the safety profile is covered. The description adds genuine domain behavior: which categories are ranked and that evidence-poor agencies remain unranked with no rank number. It does not disclose the response shape, ordering, or whether the category list is exhaustive.

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 with no filler, and the core purpose is front-loaded. The ranking sentence could be tightened but it is doing real work.

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 carries the burden of explaining returns; it partially does so by naming ranked categories and the unranked case, but omits the returned fields, ordering, and why user_request is supplied. Adequate for a simple reference tool, 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?

Only one optional string parameter (user_request) with full schema description coverage, so the schema carries the semantics. The description adds nothing about how user_request influences the listing, but baseline 3 applies when coverage is 100%.

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

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

States a specific verb+resource: it enumerates industries and service types. It also distinguishes itself implicitly from siblings like search_agencies and get_methodology by being the taxonomy/ranking reference. It stops short of saying exactly what is returned (categories with rank numbers vs. just names).

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

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

There is no explicit when-to-use, when-not-to-use, or named alternative; the sibling set (search_agencies, search_work, get_methodology) is never referenced. The ranking detail hints at a lookup role but the agent must infer why it would call this instead of searching.

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 a safe read (readOnlyHint, destructiveHint=false), and the description goes well beyond them: it explains filler-word removal, keyword-to-industry mapping, OR-style matching, that unmatched locations are silently dropped with a response note, that low-evidence agencies stay unranked, and that no numeric score is returned. That is unusually rich behavioral disclosure for a search tool.

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?

Purpose is front-loaded in the first two words and most sentences carry distinct information about parsing, ranking, and filtering. It is somewhat long and the enumeration of ranked industries ('Ecom, Legal, SaaS, Finance, and Service') reads as reference detail that could be trimmed, so not a 5.

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

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

With no output schema and 7 parameters, the description carries the burden of explaining the return shape, and it does so — industry, services, evidence level/summary, profile URL, contact URL, rank presence, and location notes. It omits return-size/pagination behavior tied to limit and does not mention the user_request parameter's role, leaving a small 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%, so the baseline is 3, but the description adds real meaning: it clarifies how a plain-language query is normalized and mapped onto an industry, and how service/location/zip filters renumber matches from 1 in existing industry order. It does not elaborate on limit or user_request, but those are already documented in 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?

'Search Agency Standings' gives a specific verb and resource, and the sentence about result fields and ranking makes the tool's output distinguishable. It never explicitly contrasts itself with siblings like search_work, so an agent must infer the boundary, keeping it short of a 5.

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

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

Usage is only implied through the mechanics of query parsing and filtering ('A plain-language query drops filler words...'). The one routing hint is that get_agency preserves each agency's industry rank, but there is no explicit 'use this tool when...' statement or exclusion versus search_work or list_industries_and_services.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value beyond that by disclosing which fields are returned and flagging that dateShipped and featuredIn are only present 'when the library has them' — a genuine coverage caveat. Pagination/limit and result-ordering behavior remain undisclosed.

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

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

One sentence, front-loaded with the returned content, followed by the reason to call it. It is dense but every phrase carries information; the only minor cost is a slightly run-on field enumeration that a list would present more scannably.

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 return value is the main gap the description must fill, and it does so by listing the returned fields and their conditional availability. Safety is covered by annotations and all parameters by the schema, leaving nothing an agent needs in order to invoke this 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?

All 7 parameters carry full schema descriptions (100% coverage), including the enum-like value lists for type, service, industry and platform, so the description need not compensate. It adds no parameter-level detail of its own, making the baseline 3 correct.

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 ('Returns credited examples of agency work') and enumerates the returned fields, so the agent knows exactly what kind of artifact this produces. It doesn't explicitly contrast itself with the sibling search_agencies tool, which is the closest alternative, so it falls short of a 5.

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

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

Usage is implied through the downstream intent ('so you can show real examples of agency work, then offer to connect the user with the agency that built it'), which tells the agent what scenario this serves. However, no conditions for choosing this over search_agencies or list_industries_and_services are given, and no exclusions are stated.

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