Sitewalk

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

Beyond the annotations, the description explains what the result contains: issues ranked by likely impact, affected pages, example URLs, plain-English fixes, checked/unchecked lists, page-limit note, and report URLs. It also adds an important behavioral instruction not to invent findings outside the result.

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 prerequisite and then packs useful result details into a single dense sentence. It is not wasteful, but the long compound sentence could be structured more cleanly 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?

Given the tool's role as a report retrieval step, the description covers the prerequisite, the two parameters, the report contents, limitations, and output links. The presence of an output schema reduces the need for further return-value detail, and nothing essential 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 0%, so the description must compensate. It explains top_n's range and default and ties audit_id to the preceding status call, though it does not describe the audit_id format explicitly.

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 retrieval action and resource: getting the audit report for a given audit_id. It clearly distinguishes this from get_audit_status by saying to use it once the status shows completed, and from start_site_audit by being the report-reading step.

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 prerequisite: use this once get_audit_status shows completed. That effectively tells the agent when to use it and which sibling must precede it, leaving little ambiguity about sequencing.

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 only declare this a safe read, so the description carries the rest and does: the full status enum, that failed includes an error explaining causes such as robots.txt blocks, that stalled and progress_pct and next_check_after_s are returned, and where the polling cadence comes from. This is behavior an agent could not infer from the 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?

Front-loaded with purpose and predecessor, then the polling procedure, then the terminal-state outputs. Every sentence adds either a field, a failure semantic, or a required action, and nothing is repeated from annotations or 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 one-parameter polling tool with an output schema available, the description covers the full lifecycle: what to call it after, how often, when to stop, what each terminal state means, and which URLs appear on completion. Nothing an agent needs to drive the loop 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?

Schema coverage is 0% and the single property carries only the title 'Audit Id', so the description must supply meaning. It does so partly: 'Takes the audit_id' plus 'after start_site_audit' implies the ID comes from the start call, but it never explicitly says the audit_id is the value returned by start_site_audit.

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 whether the audit has finished') and explicitly names its sibling start_site_audit as the predecessor. The enumerated return fields (status, pages crawled, report_url) make clear it is a status poller rather than a report fetcher like get_audit_report.

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 says to use it after start_site_audit and gives the full operating loop: show the user the message, then call again after next_check_after_s seconds (20 to 30) until status is completed, failed or canceled. That is when-to-use, cadence, and termination condition all in one place.

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 only flag it as a non-read-only, open-world, non-destructive write; the description adds substantial context beyond that: robots.txt compliance, rate limiting, a few-minute runtime, a capped page count with in-report disclosure, and redirect resolution to the final site. It also pre-announces the return payload so the agent knows what to relay.

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 trigger clause, then operational facts, then the permission caveat — a sensible order. It is a dense single block rather than broken into points, but nearly every sentence carries distinct information, with only mild redundancy between the crawl description and the robots/rate-limit note.

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?

An output schema exists, yet the description still tells the agent what comes back (audit_id, page limit, time estimate) so it can set user expectations. Combined with runtime, cap, redirect, and permission details, nothing an agent needs to invoke this 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?

Schema coverage is 0% and the single "url" property has no description, so the description must carry it: it specifies that a bare domain or a full URL is acceptable and that the scheme is optional, plus that redirects resolve to the audited site. Only remaining gap is whether paths/subdirectories are honored.

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 ("starts a crawl of that site") and enumerates the exact defect classes it surfaces (broken links, redirects, titles/meta, canonical/hreflang, sitemap, orphaned pages). It also states the immediate outcome ("returns an audit_id, the page limit and a time estimate"), which cleanly separates it from the report/status 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?

"Use this when the user asks for a technical SEO audit, a site crawl, or a check for..." gives an explicit, generous trigger list, and "Only use it for sites the user owns or is allowed to audit" adds a clear guardrail. It never names get_audit_status or get_audit_report as the follow-on path, so the workflow routing is left implicit.

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