NotWorking

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description goes further by detailing the return shape: one-sentence summary, service, every listed access path with failure reports over 1h/24h/7d, what_failed values, and how to report, plus the listed:false behavior for unlisted targets. It does not mention rate limits or auth requirements, but adds substantial behavioral context beyond 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?

The content is dense but front-loaded with the core question and use cases. It is a single long paragraph rather than bulleted, which slightly reduces scanability, but every sentence contributes useful information about when to use it and what it returns.

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 complexity (multiple target types, failure reports over time windows, listed vs unlisted behavior) and the presence of an output schema and annotations, the description is complete enough for an agent to select and invoke it correctly. It covers use cases, target formats, return summary, and edge cases.

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 baseline is 3. The description adds meaningful examples of target values beyond the schema: URLs, access-path IDs with formats like clawhub:<owner>/<slug>, skills.sh:<owner>/<repo>/<skill>, and MCP Registry names like io.github.<owner>/<server>. It does not describe the optional 'type' parameter, which the schema covers.

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 (check/look up) and resource (a site, URL, MCP server, or skill) and explains the core question it answers: whether something is down for everyone or just the caller. It distinguishes itself from the sibling 'report' by focusing on checking status rather than submitting a report, though it does not explicitly name the sibling.

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 a detailed, explicit list of when to use the tool (site down, unreachable, timeout, blocked, login loop, MCP connection failure, tool error, skill failure). It does not state when not to use it or name the alternative 'report' tool, but the context is very clear.

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 the write/safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower, yet the description still adds substantive behavior: the submission is anonymous, must never contain personal data, booking details, credentials or query-string URLs, and the note is never shown to other agents. It stops short of describing confirmation, deduplication or any rate limit on repeated reports, leaving a small gap.

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?

Purpose and privacy constraints are front-loaded, and the long enum glossary is load-bearing because the schema supplies no value descriptions. It is dense rather than bloated, though the inline enumeration is bulkier than ideal and could have been trimmed given some values are self-explanatory.

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 six parameters, a write operation and an output schema already present, the description covers the remaining agent-facing questions: where the target comes from, what each failure code means, the privacy/anonymity rules, and the failure-source exclusion. Nothing needed to call 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 100%, so the baseline is 3, but the description genuinely exceeds the schema by defining every what_failed enum value ('site_unreachable: ...', 'bot_block: ...') which the schema lists without per-value text, and by clarifying that target is 'which access path failed' and can be an id or URL. That is real added meaning, though the optional note/type/country/agent_type parameters are largely left to their schema descriptions.

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 first sentence states a specific verb and resource — 'Report that an access path failed for you' — and the rest of the text pins down exactly what an 'access path failure' means. It is easily distinguished from its sibling check_status, which it explicitly names as the source of the id it consumes.

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 precisely when to file a report ('use the access-path id from check_status, or the URL you used') and, unusually for this kind of tool, when NOT to — failures caused by the agent's own tools, permissions or settings, with a concrete counterexample ('a fetch tool that refuses a domain'). Nothing 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.