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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful context beyond the annotations: possible warnings (denounced instrument, not in force, OCR text, amendments to verify), the authoritative source (official PDFs on impots.gouv.fr), corpus date and licence.

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?

Purpose is front-loaded in the opening clause, and the remaining sentences each carry content (return payload, parameters, source/date/licence). The bilingual duplication of the source/licence sentence adds length without new information, keeping it short of a 5.

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 burden of describing the response, and it does so (exact text, instrument title, official PDF, amendment notes, warnings). Source, corpus date and licence round out the context; only the ambiguity of `acte` vs `pays` precedence and pagination/availability limits go unaddressed.

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 a 3 is the baseline. The description does add meaning beyond the schema by clarifying that `objet: successions` selects the succession convention specifically and by giving article-format examples (18, 1er, 28 bis), which slightly exceeds the structured field 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?

The description states a specific verb and resource: returning the 'Texte EXACT' of one article of a French tax treaty, with the instrument title, official PDF, amendment notes and warnings. An agent can distinguish it from the search-oriented siblings, but no sibling tool is named explicitly, so differentiation is inferred rather than stated.

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 tells the agent how to drive the lookup (give `pays` or `acte` plus `article`), and when to use `objet: successions` for the succession convention, plus the optional `paragraphe` narrowing. There is no explicit when-not-to-use guidance or named alternative (e.g. use conventions_search to find an article), so it stops short of full routing advice.

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