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

Annotation contradiction: readOnlyHint=true claims no observable state changes or side effects, but the description says 'Publish', 'Retention 1-30 days', 'Priced $0.01 per call', and mentions a prepaid credit header and billing model. Publishing a hosted page is an observable creation event, so the description directly contradicts the annotation. Per rubric this forces a score of 1 despite otherwise useful behavioral details.

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 purpose, then sibling contrast, then retention/storage placement, then auth and pricing. Every sentence carries a decision-relevant fact. It loses a point only for mild redundancy such as repeating 'Required input: text' when the schema already declares it and for being a dense single paragraph.

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, the description covers purpose, output format, sibling distinction, retention bounds, storage origin, script-safety, pricing, credit headers, and auth requirements. An output schema exists, so return-value documentation is not the description's job. An agent has enough context to decide when to call it and how to invoke 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?

Schema description coverage is 100%, so the baseline is 3. The description mostly reinforces schema content ('Required input: text', 'Send Markdown (or HTML)') and adds one genuinely new semantic bound: 'Retention 1-30 days' for ttlDays. It does not meaningfully enrich title or format beyond what the schema already provides, so modest extra value, not enough for a 4.

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 opens with a concrete verb and resource: 'Turn a report into a link a human can open' and specifies the output as a URL rendered as a real page. It also explicitly distinguishes this tool from file-slot: file-slot is for bytes the agent fetches back, while file_publish is for reports a human reads.

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 names the sibling alternative file-slot and gives the exact deciding criterion: bytes the agent will fetch back versus a report somebody has to read. This is explicit when-to-use guidance rather than leaving the agent to infer from context.

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