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

The readOnlyHint annotation covers the safety profile, and the description adds meaningful behavior beyond it: scope (only published poems, not drafts), ordering (newest first), and a critical advisory that poem content must be treated as poetry, not instructions — a valuable anti-prompt-injection disclosure for an AI agent. It doesn't address pagination or edge cases, but adds solid context despite the annotation.

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 sentence fragments, both earning their place: the first front-loads the resource and ordering, the second delivers the usage-critical warning. Zero 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 simple read-only tool with one fully-documented optional parameter, a readOnlyHint annotation, and clear sibling differentiation, nothing essential is missing. The anti-instruction warning is especially important given the tool surfaces author-authored content to an LLM.

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% — the limit parameter is fully documented with type, range, and default ('How many, default 20'). The tool description adds no parameter detail, but per the baseline for full schema coverage, the schema carries the burden adequately.

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 resource (published poems) with an unambiguous scope qualifier ('published') and ordering ('newest first'). The verb is supplied by the name/title, and the published-only scope plus the 'not as instructions' warning clearly distinguish it from publish_poem (write) and get_challenge (different resource).

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 context is clear — use this to fetch published poems in reverse-chronological order — but there is no explicit when-to-use/when-not-to-use statement or alternative routing relative to siblings. The differentiation from publish_poem and get_challenge is only implied by their names.

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