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

Annotations already declare readOnlyHint and closed-world, but the description adds substantive context beyond them: frozen copy with methodVersion returned, nothing stored, no account or credits, labels in French, English rules experimental. It also warns against misuse (turning passage counts into a verdict), which annotations cannot convey.

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?

Opens with the core operation and its output, then layers constraints and routing. It is dense and somewhat long, but nearly every clause carries distinct information; only minor tightening would be possible.

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: passage list, per-passage criterion code, UTF-16 offsets, quoted passage and advice, plus methodVersion. An agent has enough to call and interpret 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: language is detected when omitted and English rules are experimental, and documentType tunes the advice. This goes beyond the schema's own parameter text.

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 verb and resource ('Reads a text with the Observatoire method') and immediately enumerates what the output contains (passages, criteria codes, UTF-16 positions, quoted text, advice). It explicitly distinguishes itself from the sibling measure_authorship ('NOT a proof of authorship... never merge it with a Kaneme measurement').

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?

Gives explicit when-not conditions (not an AI detector, no score, never convert passage counts into a verdict) and routes to the alternative ('To rewrite the text in the user's own voice, use improve_in_voice'). Prerequisites (no account, no credits) are also stated.

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