LLMready

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

Annotations already flag openWorldHint=true and non-idempotent/non-readonly, so the safety bar is lower. The description adds genuinely non-obvious behavior: a live crawl, a credit cost, and a Pro-authentication requirement — all material before invoking. It stops short of disclosing whether runs are persisted or reusable via the returned report link.

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: the first front-loads what the tool does and returns, the second carries cost and auth preconditions. 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 one-parameter tool with no output schema, the description adequately enumerates the return payload and states cost/auth. It could go one step further by noting whether the audit is persisted and retrievable via get_audit or the report link, but nothing critical 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 coverage is 100% and the url parameter already carries a format example, so the schema does the heavy lifting. The phrase 'public website' adds one real constraint (no intranet/auth-gated URLs), but no other parameter detail is added. 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?

States a specific verb ('crawl a public website live') plus the exact deliverable (0–100 score, grade, category scores, prioritized fixes, shareable report link) and names the audience/targets (ChatGPT Search, Perplexity, Gemini, Claude). This clearly separates it from read-only siblings like get_audit, list_audits, and quick_check.

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 prerequisites ('costs 1 credit', 'requires signing in with LLMready Pro') which is useful context for whether to call it. However, it never says when to prefer this over quick_check, nor that get_audit retrieves a previously run audit — the agent must infer sibling routing without help.

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 openWorldHint=true and non-idempotent, non-destructive write behavior, so the bar is lower. The description still adds genuinely non-obvious detail: a 1-credit cost, an auth requirement, and the crucial fact that the output is 'ready to upload' rather than uploaded for you — clarifying that this does not mutate the target site.

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 carrying distinct payload: what is produced, what it costs, and what is required to run it. The deliverable is front-loaded before the cost/auth caveats, 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?

For a single-parameter tool with no output schema, the description covers the important ground: what the artifacts are, their format, and the auth/cost gate. It leaves out roughly how long a crawl takes, what is returned (file contents vs. download links), and failure behavior, which an agent estimating the call would want.

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 already documented as 'Website URL or bare domain'. The description adds no syntax, format, or domain-vs-path guidance beyond the schema, so the baseline 3 applies. The 'key pages' phrasing hints at crawl scoping but does not tell the agent what it can influence.

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 chain (crawl, generate) and two specific artifacts (/llms.txt and /llms-full.txt) with their format (Markdown, spec-compliant). An agent can distinguish this from the sibling validate_llms_txt or audit_url purely from this sentence, since none of those produce files.

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 real prerequisites — costs 1 credit, requires signing in with LLMready Pro — which is more than most tools offer. But it never states when to pick this over validate_llms_txt (generating vs. checking an existing file), so the choice among siblings is 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 declare readOnly, idempotent and closed-world, so the description does not need to restate safety. It adds genuinely new behavior: the call is free (no credit cost) and gated on an LLMready Pro session — information an agent cannot derive from annotations and must know before choosing this tool over a metered one.

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 sentences: what it returns comes first, then the cost signal, then the auth prerequisite. Every sentence carries decision-relevant information and nothing is repeated from the schema or annotations.

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, so the description correctly enumerates the returned fields, and it covers both the auth gate and the billing characteristic — the two things most likely to cause a failed or misrouted call. Missing only edge behavior such as what happens for an unknown or expired audit id.

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 id parameter already documents its uuid format and provenance from audit_url or list_audits. The description only echoes 'by id', so it adds nothing beyond the schema; 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 (fetch) and resource (a saved audit) plus what the payload contains (score, failing checks, AI crawler access, fixes). 'Saved' implicitly distinguishes it from audit_url, which creates a new audit, 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?

Makes clear this is a retrieval-by-id path and supplies the two selection-relevant preconditions: no credit cost and LLMready Pro sign-in required. It stops short of explicitly telling the agent to use audit_url when no id exists or list_audits to discover ids.

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 closed-world, so the safety profile is covered. The description still adds real value by disclosing the billing behavior ('No credit cost') and the authentication requirement ('Requires signing in with LLMready Pro'), neither of which is in 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?

Two short sentences, front-loaded with the outcome and followed by the two operational caveats. There is no filler and nothing a reader would need to skip past.

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-param read tool with no output schema, the description conveys what is reported (used and remaining credits, monthly window) plus the auth and cost conditions. A hint about the return shape (e.g. a numeric breakdown) would close the last gap, but no critical calling information 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?

Zero parameters, so there is nothing for the description to disambiguate; the baseline applies. Nothing in the description misrepresents the (empty) input surface.

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 ('Show') and resource ('LLMready credits used and left this month'), and the scope ('this month') makes it trivially distinguishable from the sibling audit/generation tools. An agent can tell immediately that this is a quota/usage lookup, not an audit action.

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 credit cost. Requires signing in with LLMready Pro.' gives clear invocation conditions and a prerequisite the agent would otherwise not know. It stops short of naming when-not-to-use or pointing at an alternative, but no sibling tool overlaps this function, so the exclusion set is naturally empty.

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 closed-world scope, and the description adds genuinely new behavior: default newest-first ordering, zero credit cost, and an authentication prerequisite. Those are exactly the operational facts annotations cannot express.

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 tight sentence carries resource, ordering, filtering, cost and auth in that order of importance. Nothing is redundant or padded.

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 list tool with annotations and no output schema, the description covers the callable conditions and result ordering well. It does not hint at what an audit record contains or how the default page size interacts with results, a minor gap given no output schema exists.

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 both parameters are fully documented in the schema, so the baseline is 3. The description only reinforces that the domain filter is optional and adds ordering semantics; it says nothing about the limit parameter's default or 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 resource (list audits) plus ordering ('newest first') and scoping ('optionally for one domain'), which naturally separates it from singular siblings like get_audit and audit_url. It does not name any sibling explicitly, so it falls short of the top tier.

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?

Gives clear qualifying context: the domain filter is optional, there is no credit cost, and LLMready Pro sign-in is required, which tells the agent when the tool is callable. It stops short of naming alternatives such as get_audit for a single audit or audit_url for running a new one.

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, and the description adds useful context beyond them: exact rate limits (10/min, 100/day per IP, per account when signed in), that the check runs live against a public site, and that no report is saved. These are exactly the operational details an agent needs before calling it repeatedly.

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 key free-tier and rate-limit details, then what the tool returns, then the Pro alternative. It is dense but every clause carries information, though the first sentence is somewhat packed with free-tier terms.

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, and the description fully explains what the tool returns: score, grade, category scores, crawler allowances, llms.txt status, and top 3 fixes. Combined with rate limits and the no-saved-report detail, an agent has everything needed to call it 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?

There is only one parameter, and the schema documents it at 100% coverage with format examples (full URL or bare domain). The description adds no additional syntax or format guidance, so 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?

States a specific verb and resource: it checks a public website live and returns a 0–100 AI search readiness score, grade, category scores, crawler allowances, llms.txt presence, and top 3 fixes. It also explicitly distinguishes itself from audit_url (Pro), which lists every failing check with a shareable report and badge.

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?

Names the alternative tool (audit_url) and the condition that selects it: full failing-check listing and shareable report. It also gives practical context on when this tool is usable, with no sign-in, Pro, or credits needed.

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, open-world, and idempotent behaviors, so the description's added value is auth and cost: 'No credit cost. Requires signing in with LLMready Pro.' That is a genuinely useful constraint an agent cannot infer from the annotations or the schema, as is the note that network fetching occurs for the url path. Both behaviors are documented explicitly rather than left implicit.

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 core validation action before the input modes and then the auth/cost note. Every clause carries information the agent needs, and nothing is repeated from the name or the schema.

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 read-only, two-parameter validator with no output schema, the description supplies the important context: auth requirement, zero cost, open-world fetching, and the shape of the result (errors and warnings by line). It could go further by describing the response structure, such as how many errors or warnings are returned or whether a pass/fail verdict is included.

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 each parameter is already documented individually. The description adds the relationship between them, 'pass content ... or url', which clarifies that the two are alternative modes rather than combined inputs, and the schema itself encodes no oneOf requirement. This is a modest but real semantic addition 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: check llms.txt content against the llmstxt.org proposal and list errors and warnings by line. That is unambiguous, and the name/behavior clearly separates it from generation (generate_llms_txt) and audit siblings. It stops short of explicitly naming which sibling to use instead for what, so it is clear rather than fully differentiated.

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 tells the agent the two mutually exclusive usage modes (pass content to check text, or url to fetch and check a site's live /llms.txt) and states the prerequisites: sign-in with LLMready Pro and no credit cost. It does not say when to prefer this over audit_url or quick_check, so the usage context is clear but not exclusionary.

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