AEO Lookup

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true. The description adds useful behavioral context beyond that: the result is a pound range plus two or three insights, it is partial by design, and no key is required. It does not discuss assumptions or accuracy limits, so it is strong but not 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?

The description is front-loaded with the core estimate and then layers inputs, limitation, access note, and docs link. It is dense but every clause carries useful information, with only minor room to tighten.

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 must explain the return value, and it does: a pound range with two or three insights. It also explains the deliberate partiality and points to the full audit. It is nearly complete, though it could be clearer about calculation assumptions.

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 schema already documents all four parameters. The description still adds meaningful semantics by naming the default sources: ONS 2025 UK median for hourly pay and Department for Education ranking for sector exposure.

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: it estimates annual savings in pounds for a UK business from admin automation. It also scopes the calculation inputs. However, it does not explicitly distinguish this tool from siblings such as calculate_ai_time_saved or estimate_ai_staff_impact, 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?

The description implies usage by calling the result partial and pointing to the free AI audit for a full breakdown. But it does not clearly state when to choose this tool over sibling calculators, nor does it provide explicit when-not 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 readOnly/idempotent/openWorld, so the safety profile is covered; the description adds genuinely new context: the result is a range plus the biggest-saving task, the per-task shares derive from IPPR and McKinsey research, and no API key is needed. It stops short of noting that all-zero inputs produce a trivial result, but the added value over annotations is real.

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 tight sentences: purpose and task enumeration first, then return shape, cost and docs link. The parenthetical task list is long but earns its place by mapping to the eight parameters. No filler sentences.

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 must explain the return value, and it does: a range plus the highest-saving task. Combined with the fully documented schema and read-only annotations, an agent has everything needed to call this correctly without opening the docs link.

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 every parameter already documents its unit, range and default, so the schema carries the load. The description contributes the framing that inputs are hours per person per week across seven task types and that people scales it to a team, which is mildly additive but not new syntax or format 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 and resource ("Estimates the hours a week AI could save") plus the exact input domain: seven named task types. An agent can tell this is a time-savings estimator rather than an audit or readiness score. It does not, however, distinguish itself from the sibling calculate_ai_savings, which sounds like a near-duplicate.

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?

"one person or a team" and the per-task default of 0 imply how to call it, and "Free, no key" removes an auth concern. But there is no explicit when-to-use / when-not guidance and no routing away from calculate_ai_savings or estimate_ai_staff_impact, so the agent must infer the boundary between these overlapping calculators.

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 readOnly, idempotent, and openWorld, so the bar is lower; the description still adds real context by naming the four signal types inspected and clarifying that it covers 20 crawlers split into search/user vs training categories. It omits pacing/rate-limit behavior and what a failure report contains, which keeps it from a 5.

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 core capability is front-loaded in the first sentence, with the differentiating crawler-classification note and the free/no-key/docs line following as short support. The crawler list ('and 14 more') is slightly padded but carries genuine scope 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 no output schema, the description should convey the shape of the result (per-crawler allow/deny verdicts plus the rule that caused it), but it only says what is evaluated, not what comes back. For a diagnostic tool with 20 crawlers and multiple rule sources, an agent cannot predict the response structure from this text alone.

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 only two parameters, so the schema already documents url and path fully, including the https:// normalization and the path override. The description adds no further detail about how `path` interacts with the URL's own path or what happens when a site-level vs page-level check is requested.

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 uses a specific verb (checks) plus a concrete resource (whether named AI crawlers may read a page) and enumerates the exact evidence sources: robots.txt RFC 9309, robots meta, X-Robots-Tag, and firewall user-agent refusal. It is clearly distinguishable from siblings like validate_llms_txt or check_structured_data, which target different artifacts.

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 rather than stated: the note that search/user crawlers 'decide whether you can be cited' hints at when this matters, but there is no explicit 'use this when…' or exclusion against run_aeo_audit or score_answer_readiness. The 'Free, no key' note removes a prerequisite question but is not routing 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 read-only, idempotent and open-world, so the safety profile is covered; the description adds real value beyond that with the methodology (DfE 2023 ranking) and the 'Free, no key' cost/auth note. It also discloses the shape of the result, which matters since there is no output schema.

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 dense sentence carries purpose, methodology and outputs, followed by a short access note and a docs link — front-loaded with no filler. The opening sentence is long but every clause contributes.

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 takes on the job of telling the agent what comes back, and it does so at a high level (rating plus task-share plus leading tasks). An agent has enough to call it correctly and interpret the result, though exact output fields are not spelled out.

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 parameter is a 22-value enum, so the schema does the heavy lifting. The description only adds the qualifier that occupations are UK-specific, which is a small but useful constraint 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?

States a specific verb (rates) and resource (a UK occupation's AI exposure) plus the concrete outputs: a high/medium/low rating, the share of tasks AI can do, and which tasks it reaches first. That clearly separates it from sibling tools like estimate_ai_staff_impact, though the distinction is left implicit rather than named.

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 description — use it to score a single occupation's AI exposure — but there is no explicit when-to-use or when-to-use-another-tool guidance, and no mention of the sibling calculators an agent should prefer for other questions.

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 safety (readOnlyHint, idempotentHint, openWorldHint), so the description's contribution is the operational detail: it is free with no API key, and it enumerates exactly which nine schema.org types get validated, which discloses a real coverage limit an agent would otherwise not know. It stops short of stating what happens on fetch failure or when no JSON-LD is present.

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 primary action, then the scoring detail, then the free/no-key and docs notes. It is one long run-on sentence whose clauses all carry information, but a bulleted structure would make the enumerated type list easier to scan.

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 describing the returned content (extracted blocks, type list, missing-property flags, entity score). What is missing is edge-case behavior — no structured data found, unreachable page, or whether the raw HTML is parsed versus rendered output.

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 parameter with 100% schema description coverage, and the schema already explains that https:// is added when missing. The description adds no syntax, format, or constraint information 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?

Specific verb chain and resource: extracts JSON-LD blocks, lists schema.org types, flags missing required/recommended properties, and scores entity signals. The resource (structured data on a URL) is clearly distinct from the llms.txt and crawler-access siblings. It does not explicitly say how it relates to run_aeo_audit, which is the one sibling that could plausibly overlap.

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 content ('check a page's structured data') but there is no explicit when-to-use statement, no prerequisites, and no routing away from run_aeo_audit or the other siblings. An agent can infer the use case but must decide on its own when this beats the broader audit 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 declare readOnly/idempotent/openWorld, so the bar is lower. The description adds genuinely new context: 'Measures tasks, not people' sets methodology expectations, 'ordered by the Department for Education's exposure ranking' discloses the model behind results, and 'Free, no key' states the auth requirement.

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 core purpose in the first clause, then scope caveats. It is dense and every clause carries information, though the single long run-on sentence could be split for readability.

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, but the description conveys the return shape ('full-time roles' worth of tasks') and the ranking basis, so an agent knows what to expect. Only the exact result structure (per-role breakdown vs totals) remains unspecified.

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 clear per-role descriptions and defaults, so the schema does the heavy lifting. The description only adds that there are seven role groups, which is already visible from the schema, so 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 output unit ('estimates how much of a team's work AI could take on today, as full-time roles' worth of tasks') plus the input basis (headcount in seven role groups). This clearly separates it from siblings like calculate_ai_savings and check_job_ai_risk.

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 context is implied by the description ('team's work', role-group headcounts), and 'Free, no key' lowers the barrier, but it never explicitly says when to prefer this over calculate_ai_savings, calculate_ai_time_saved, or check_job_ai_risk. No exclusions or prerequisites are stated.

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 readOnly/openWorld/idempotent, so the safety profile is covered; the description adds genuinely useful context beyond that — 'Free, no key' (auth/cost), 'up to 24 pages' (a hard crawl cap) and 'Returns the file as text' (output form is textual, not a saved file). It stops short of saying what happens when a sitemap is missing or how long a run takes.

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 the verb and artifact, zero filler. The first sentence is dense with parenthetical detail but each clause carries real information; the docs link is a reasonable trailing pointer.

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 generator with no output schema, this covers cost, auth, output form, and crawl scope — enough to call it correctly. Edge-case behavior (no sitemap, unreachable site) and the max_links/24-page interaction are the remaining 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 100%, so both parameters are already documented in-schema; baseline is 3. The description adds indirect meaning about what url feeds (home page, sitemap) but adds nothing about max_links, and notably doesn't reconcile the 100-link maximum with the stated 24-page read cap.

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 artifact ('Drafts an llms.txt for a site') and goes on to enumerate exactly what the draft contains: site name/summary from the home page, sitemap pages grouped by section, titles and descriptions. This is plainly distinguishable from validate_llms_txt (checking an existing file) and the audit/scoring siblings.

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 phrase 'for a person to edit before publishing' implies this is a drafting step in a workflow, but the description never says when to pick it over validate_llms_txt, nor any precondition (sitemap required?) or exclusions. Usage is inferable, not stated.

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 readOnly, idempotent and openWorld, so the description is not carrying the safety burden; instead it adds genuine value by disclosing the scoring formula (mean of crawler, schema and answer-readiness) and explaining why llms.txt is reported but excluded. Cost/auth ('free, no key') and a docs link are also given, though rate limits and failure behavior are not.

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 tight sentences, front-loaded with what runs and what is returned; the scoring rule and the llms.txt exclusion each earn their place because they change how an agent interprets the output. The docs URL is placed last where it belongs.

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 must stand in for return-value semantics; it does so at a coarse level (four check results plus an overall score, with the scoring basis stated). It stops short of describing per-check result shape or error responses for unreachable URLs, which is the remaining 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?

Only one parameter and the schema documents it fully at 100% coverage, including the https:// normalization behavior, so the baseline is 3. The description's phrase 'one address' reinforces the single-URL scope but adds no format or edge-case detail 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?

States a specific verb and resource ('Runs all four checks on one address') and enumerates the four checks, which map directly onto the sibling tools (crawler access, structured data, llms.txt, answer readiness). An agent can immediately tell this is the aggregate/superset tool versus the single-check siblings.

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 context is clear: one address, all four checks, free with no key. Naming the four checks implicitly frames the alternative (call the individual sibling tools for a single check), but it never states when to prefer the granular tools or what to do with a multi-page site.

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, so the safety profile is covered. The description adds meaningful context beyond the annotations: the tool is free, needs no API key, returns a score out of 100, and names the two biggest gaps, though it does not discuss edge cases such as omitted parameters or output formatting.

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 front-loaded with the core purpose and result, then efficiently lists the eight dimensions and supporting details such as cost, authentication, and documentation. There is no redundant or filler text.

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 eight optional boolean parameters, no output schema, and no required parameters, the description supplies enough context for an agent to invoke the tool correctly. It explains the input dimensions, the scoring outcome, and the additional gap analysis without needing 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?

Schema description coverage is 100%, and each boolean parameter already includes a detailed explanation with its point value. The description lists the same eight categories but does not add meaning beyond what the schema provides, so the baseline 3 is 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 states a specific verb and resource: it scores AI readiness for a small business, out of 100, from eight yes/no inputs, and returns the two biggest gaps. This clearly distinguishes it from sibling calculators such as calculate_ai_savings, calculate_ai_time_saved, and score_answer_readiness.

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 usage context is implied by describing a readiness assessment for a small business, but there is no explicit guidance on when to choose this tool over sibling tools or when not to use it. It also does not mention prerequisites beyond being free and requiring no key.

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, idempotent, openWorld), and the description adds genuinely useful operational context: it is free, needs no API key, and returns results ordered by points available with a finding and a fix per check. It stops short of noting rate limits or latency, so not a 5.

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 dense sentence for the scoring scope, one for the return shape, then constraints and a docs link. The most important information (what it scores and what you get back) is front-loaded 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?

With no output schema, the description correctly compensates by explaining the return shape and ordering, plus cost/auth constraints. It is nearly complete, though it could say more about how the 14 checks are weighed or whether the target must be publicly reachable.

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 `url` parameter is fully documented in the schema, including the https:// fallback behavior. The description adds no parameter-level detail beyond what the schema provides, 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 ('Scores a page out of 100 on 14 published checks') and enumerates the checked dimensions, so the agent knows exactly what it produces. It does not explicitly differentiate itself from overlapping siblings like run_aeo_audit or check_structured_data, which keeps it below 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 — check a page's answer readiness — but there is no explicit when-to-use/when-not guidance and no mention of the alternative tools in the sibling set. Given the overlap with run_aeo_audit and check_structured_data, an agent must infer which to pick.

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, idempotent and open-world behavior, so the bar is lower; the description still adds real operational detail — link testing capped at eight same-site links, the llms-full.txt existence probe, and the free/no-key access model. It does not describe output shape, but with no output schema that is a minor omission for a read-only validator.

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 behavior and scope come first, then access/cost, then docs link — a sensible front-loading. One clause ('States the evidence on how little the file is read') is vague about what actually gets returned, but the rest earns its space.

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 only two fully documented parameters, no output schema and safety already declared in annotations, the description supplies what is missing: the validation rules applied, the link-testing limit, and the extra llms-full.txt check. An agent has enough to call it and predict the kind of result.

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 baseline would be 3; the description goes slightly beyond by clarifying that the input may be either a site page or the llms.txt address itself, and by restating the eight-link cap that constrains check_links.

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 concrete verb-and-resource pairing: fetches /llms.txt, validates it against the llmstxt.org proposal, link-tests, and checks for llms-full.txt. The validate-vs-generate split from sibling generate_llms_txt is inferable, but 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 implied (check a site's llms.txt conformance) and the 'Free, no key' note removes a friction question. However, nothing says when to prefer this over check_ai_crawler_access or run_aeo_audit, and no exclusions are given.

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