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

Annotations already declare this a safe, idempotent, closed-world read, so the bar is lower, and the description still adds real behavioral context: the biography is capped at roughly 1,500 characters, the summary is one line, and the poem list is truncated at 10 with links. Those truncation limits are exactly what an agent needs to know before deciding whether it also needs another tool. It does not say what happens when the name or slug matches nothing.

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 dense sentence with the resource and lookup modes front-loaded and the return inventory following; no sentence is filler. The comma-list of return values is slightly heavy but each item is informative rather than redundant.

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 no output schema, the description carries the return-value burden and does so thoroughly, listing the biography, its summary, poem count, poems with links, and the page. Combined with annotations that cover the read-only safety profile, only the not-found behavior and the name-vs-slug relationship are 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 both parameters already carry examples, so the baseline is 3. The definition does add genuine meaning by glossing slug as "the last part of the poet page URL", which the pattern alone does not convey. It leaves unaddressed whether name and slug are alternatives or must be supplied together, which is the one semantic gap the schema does not resolve.

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?

"A poet in the library by name or by slug" plus an explicit inventory of what comes back (biography, summary, poem count, up to 10 poems, poet page) tells an agent exactly what this retrieves. It reads as a noun phrase rather than a verb+resource, and it never names or contrasts with siblings like get_poem or find_poems, so it stops short of a 5.

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?

There is no when-to-use guidance: nothing says to reach for this rather than find_poems (search) or get_analysis (interpretation), and no exclusion or prerequisite is stated. The only procedural hint is 'by name or by slug', which is input-mode guidance rather than usage guidance.

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