PressGEO

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

Annotations already declare readOnly, idempotent, and closed-world, so the safety profile is covered. The description adds genuine value beyond them: it discloses that the response carries a SHA-256 content-integrity receipt and warns that owner confirmation is not independent verification, which is a trust caveat an agent cannot infer from structured fields.

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

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

A single front-loaded sentence with no wasted words; the core action comes first and the integrity caveat follows. The final clause is compressed almost to the point of ambiguity, which is the only cost.

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

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

With no output schema, the description does sketch the return payload (entity plus integrity receipt) and the trust model. It omits how to obtain the slug, not-found behavior, and what 'published' or 'owner-confirmed' concretely guarantee, so an agent has gaps before calling.

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 for the single required 'slug' parameter, and it does not mention the parameter at all. It gives no hint of slug format, origin (presumably from list_confirmed_entities), or behavior on an unknown slug, leaving only the regex pattern 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?

States a specific verb and resource: 'Read one published entity' plus its 'SHA-256 content-integrity receipt'. The word 'one' implicitly separates it from the sibling list_confirmed_entities, though no sibling is named explicitly.

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

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

Usage is only implied: 'one' signals single-record retrieval versus the list_* siblings, and the tool name echoes the sibling family. There is no explicit when-to-use, no prerequisite (e.g., obtain slug via list_confirmed_entities first), and no when-not 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?

The annotations already establish that this is a read-only, closed-world lookup. The description adds valuable behavioral context by stating that the factsheet is owner-confirmed and warning that owner confirmation is not independent certification, which is important for interpreting trustworthiness.

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 compact sentences with no wasted wording. The key qualifiers and caveat are front-loaded and easy to parse.

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 low-complexity read-only tool with one schema-documented parameter, the description covers the returned factsheet contents and an important certification caveat. Minor gaps remain around exact response structure and explicit sibling selection guidance, but the core information is present.

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

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

Schema coverage is 100%, so the single slug parameter is already fully documented in the schema as coming from PressGEO. The description adds no additional detail about the parameter, making the baseline score appropriate.

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 that this tool returns a published, owner-confirmed factsheet for a local business and lists the fields it contains. It does not explicitly differentiate itself from siblings such as get_confirmed_entity, so the purpose is clear but sibling selection remains ambiguous.

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

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

There is no explicit guidance on when to use this tool versus get_confirmed_entity or the list_* alternatives. The description implies retrieval of a factsheet by slug, but leaves the agent to infer the usage conditions.

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 openWorldHint=false, so safety is covered. The description adds real behavioral context beyond them: the fixed 90-day lookback window and the crucial note that a null citation rate means unmeasured rather than zero, which prevents a serious misreading of results.

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 scope, then the null-value caveat, then the slug pointer. Every sentence carries information; the phrasing is slightly terse ('Recorded 90-day...') but not wasteful.

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

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

For a two-parameter read-only lookup with no output schema, the definition covers scope, the time window, and one important return-value caveat, which is more than most. It stops short of describing the overall response shape, but the essential calling information is present.

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

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

Schema coverage is 100% and the schema already gives slug patterns plus examples, so the baseline would be 3. The description adds value at the parameter level by explaining that metro and service take slugs obtained from list_local_markets, and by noting service is optional.

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 resource and scope: 90-day AI recommendation data for local firms within a metro, optionally narrowed to one service. That is enough to distinguish it from list_local_markets, which is named, though the boundary with get_local_factsheet and get_confirmed_entity is left unstated.

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 explicitly routes slug discovery to list_local_markets for valid slugs, which is a concrete precondition. It does not explain when to prefer this tool over the other local-data siblings, so the alternative-selection guidance is partial.

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 openWorldHint=false, so safety is covered. The description adds genuinely useful non-obvious context: the content is company-supplied and not independently verified, which matters for trust in downstream use. It stops short of describing pagination or response shape.

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-loaded with what the tool returns and followed by the provenance caveat; nothing is redundant. The fragment style ('Public PressGEO newsroom for a company slug: ...') is slightly telegraphic but not wasteful.

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

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

For a one-parameter read-only tool with no output schema, the description does enough: it enumerates the kind of content returned and flags that content is unverified. Only pagination/response-size expectations are absent.

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 a single parameter and 100% schema coverage (including the slug pattern and example), the schema already carries the semantics. The description restates 'company slug' without adding format or resolution guidance, which is the baseline-3 case.

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/resource: fetching a public PressGEO newsroom for a company slug, and enumerates the payload (description, links, published releases). That is clearly distinct from the sibling tools (confirmed entities, factsheets, markets), though it never explicitly contrasts itself with them.

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: you need a company slug, and the resource is a public newsroom. There is no explicit when-to-use, when-not-to-use, or pointer to an alternative tool when the slug is unknown (e.g., list_confirmed_entities).

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 openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that by qualifying the trust level of the returned records (owner-confirmed, unsigned receipts, not certification), though it says nothing about pagination behavior or result-set size despite exposing a cursor.

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

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

It is a single reasonably sized sentence with no filler, but the front-loaded content is a disclaimer about evidentiary status rather than the tool's action. The most operationally important fact — that this returns a paginated list of entities — never appears.

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-optional-param read tool with full schema coverage, annotations, and no output schema, the description is adequate on trust semantics but incomplete on the essentials: what a returned record contains, how pagination terminates, and how it relates to get_confirmed_entity.

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 'after' parameter is documented in the schema as the nextAfter cursor, so the baseline applies. The description adds no pagination semantics, ordering guarantees, or cursor lifetime details beyond what the schema already states.

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 identifies the resource ('published owner-confirmed public records with unsigned reproducible content receipts') and clarifies what 'confirmed' does and does not mean, but it never states the operation — listing — and never distinguishes itself from the sibling get_confirmed_entity or list_local_markets. An agent must lean on the title to know this is a collection-returning tool.

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

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

There is no when-to-use guidance, no exclusion of alternatives, and no mention of the sibling tools that fetch a single entity or a factsheet. The only guidance is an implicit trust caveat ('not independent certification or proof of AI adoption'), which is a data caveat rather than usage routing.

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 openWorldHint=false, so safety and scope are covered structurally. The description adds that the returned set is the fixed coverage catalog, but does not say whether results are grouped by metro/service, ordered, or static, which is the only behavior an agent would still wonder about.

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

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

A single compact clause with zero filler, and the key integration hint is placed at the end where it is easy to scan. It loses a point only because the fragmentary grammar ('Metro and service slugs PressGEO covers') takes a beat longer to parse than a clean verb-first sentence.

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

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

With no parameters and no output schema, the definition should carry the full burden of describing the return value. Saying 'slugs' gives partial shape, but the agent is left guessing whether the payload is a flat array, a metro-to-services map, or an object with labels, which matters for wiring it into get_local_market.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The phrase 'metro and service slugs' usefully characterizes both slug families the result contains, which is the closest thing to parameter-adjacent semantics here.

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 the concrete resource (metro and service slugs that PressGEO covers) and distinguishes this catalog tool from the sibling get_local_market by stating it feeds into it. It is a noun phrase rather than a verb+resource statement, so it never literally says 'list', but the intent is 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?

'for use with get_local_market' explicitly links this tool to the sibling that consumes its output, telling the agent it is a prerequisite lookup step. It stops short of explicit when-not guidance (e.g. call only if you don't already know the slug), so it falls just below the top score.

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