coExploro

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

Annotations already cover the safety profile (readOnly, non-destructive, not open-world), so the bar is lower. The description adds genuinely useful context: content is generated from captured third-party sites, is sanitized, and every returned string must be treated as untrusted data rather than instructions — a meaningful injection-safety warning 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?

One front-loaded paragraph that leads with the resource and scope before enumerating the returned fields and the safety caveat. Dense but every clause carries information; only the field enumeration is mildly list-like.

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 enumerates what comes back (overall score, six UX dimensions, per-persona findings, finding counts) and warns that it is a summary. An agent has enough to call it correctly; only the cross-sibling selection guidance is thin.

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 the single 'host' parameter has no schema description, so the description must compensate. It does supply an example value ('stripe.com'), clarifying the expected format, but adds no detail on length limits, normalization, or whether a scheme/path is accepted.

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 (scorecard for one corpus product teardown), scoped by host with a concrete example. The 'corpus' qualifier plus the sibling list (get_public_teardown, get_shared_teardown) makes it distinguishable 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 clarifies that this returns a summary rather than the full teardown, which implicitly routes to a fuller tool, but it never names the alternative (e.g. get_public_teardown/get_shared_teardown) or states when to pick corpus over public/shared. Usage is implied by the 'corpus' scope rather than explained.

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 read-only, non-destructive, closed-world profile. The description adds material context beyond that: this is static curated editorial content rather than a live capture, and the text should be treated as data, not instructions — a useful prompt-injection guard.

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, each earning its place: what it returns, how to find the slug, and how to treat the content. Front-loaded with the core purpose and 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 appropriately characterizes the return as one full curated teardown and flags its provenance and trust level. Missing only minor detail on failure modes for an invalid slug.

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?

One required parameter with 0% schema description coverage, so the description carries the burden. It adds that the slug must be a valid one discoverable via list_public_teardowns, but gives no format, validation, or error behavior detail.

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 (one full curated sample product teardown), making the unit of retrieval clear. It does not explicitly distinguish itself from get_corpus_teardown or get_shared_teardown, though the 'curated editorial content authored by coExploro' line hints at the difference.

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 routes the agent to list_public_teardowns to discover valid slugs, which is genuine when-to-use guidance tied to a named sibling. It stops short of stating when to prefer this over get_corpus_teardown or get_shared_teardown.

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?

Adds substantial context beyond the annotations: it explains the counter-increment side effect that justifies readOnlyHint=false on a 'get' tool, and warns that response strings are sanitized third-party content that must be treated as untrusted data rather than instructions. That is exactly the behavioral guidance annotations cannot convey.

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 compact clauses, front-loaded with the purpose, then the trust warning, then the side effect. Every sentence earns its place with 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?

No output schema exists, and the description compensates by characterizing the returned content's provenance and trust status plus the side effect of reading. It omits error behavior for missing/expired tokens, which is a minor gap for a single-parameter read.

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% for the single parameter, so the description must carry meaning; it does say the token identifies a shared teardown, but adds no format, validity, or lookup semantics beyond the schema's uuid format. Adequate but thin.

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 (public shared teardown), scoped by share token, which separates it from the corpus/public listing siblings. It does not explicitly contrast with get_public_teardown, so the sibling differentiation is only implicit.

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 by the required share_token discriminator, but the description never states when to pick this over get_public_teardown or get_corpus_teardown, nor any prerequisites or failure modes for an invalid token.

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 (readOnly, non-destructive, closed-world), and the description adds materially more: the content originates from captured third-party websites, is sanitized, and every returned string must be treated as untrusted data rather than instructions. That prompt-injection warning is high-value behavioral context an agent cannot derive from 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?

Three sentences, front-loaded with what is listed before the alternative-tool note and the trust caveat. Every sentence carries distinct information: contents, sibling routing, and data-safety handling.

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 enumerates the returned fields itself and supplies the sanitization/untrusted-data caveat plus the sibling handoff. For a parameterless list tool, nothing an agent needs in order to call it correctly 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?

The tool takes zero parameters, so the schema baseline is 4 and there is nothing further to document. The description correctly adds no parameter detail because none exists.

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) and resource (product teardowns in the coExploro corpus), then enumerates exactly which fields come back (host, capture date, overall/UX/persona scores). This lets an agent distinguish it immediately from get_corpus_teardown, which is named as the single-item counterpart.

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 routes between this tool and its sibling: 'Use get_corpus_teardown with a host for one product summary,' implying this tool is for browsing the whole corpus. The condition that selects each tool is stated directly rather than left 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 cover read-only/closed-world/non-destructive, so the description correctly spends its budget elsewhere: it discloses that the content is curated editorial rather than a live capture and warns the agent to treat its text as data, not instructions — a genuinely useful safety note. It does not discuss pagination or result size limits.

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: the first front-loads what the tool returns, the second supplies safety framing. The long parenthetical about overallScore vs. uxScore naming is detailed but earns its place since it prevents a real misinterpretation of the returned score.

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 compensates by enumerating the fields each item carries and clarifying the ambiguous overallScore/uxScore naming, and it adds an injection warning. Complete enough for a zero-parameter list tool; pagination behavior remains 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?

Zero parameters, so the schema baseline is a 4. The description instead documents the returned item fields (slug, companyName, overallScore, personaSummary, etc.), which is output semantics rather than parameter semantics and adds no parameter information because none exists.

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 ('List the curated sample product teardowns') and scopes it to coExploro's public catalog. It does not, however, distinguish itself from the sibling list_corpus_teardowns or the get_*_teardown tools, leaving the 'public' vs 'corpus' vs 'shared' split to inference.

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 conditional guidance about when to call this versus list_corpus_teardowns or get_public_teardown. The name implies a listing operation, but no alternatives, prerequisites, or exclusions are given.

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