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

With readOnly/idempotent/closed-world annotations already covering the safety profile, the description adds real value: it discloses the corpus is a fixed set of 16 letters and that behavior switches between list mode and detail mode based on the letter id. It does not say what happens when filters match nothing (empty list vs error), which is the main remaining 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?

Front-loaded with what the shelf is, then when to use it, then the list/detail mode switch, then the exclusion. Roughly four sentences, all load-bearing, no repetition of annotation or schema content.

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 rich annotations, 100% schema coverage, and an output schema, the description supplies everything else an agent needs: corpus identity and size, content payload, the two invocation modes, and the negative case. Nothing material is missing for correct selection or invocation.

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; the description earns an extra point by explaining the mode-selection semantics — 'Without a letter id it lists the matching letters; with one it returns that letter's reading' — which the schema's per-parameter defaults do not convey on their own.

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 resource and scope: 'FamilyLore's shelf of 16 real handwritten letters from 1758 to 1943,' and spells out exactly what each entry contains (original-script transcription, English translation, contextual notes). An agent can immediately tell this apart from tools that read a user's own uploaded letter.

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 gives both the when ('someone wants to see a real historical letter' by script, language, period, year, or full reading) and the when-not ('Do not use it to read a letter or photo the person has'). The alternative sibling tools (read_letter, ask_letter) are not named, so routing is implied rather than pointed to directly.

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