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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description earns extra credit by explaining the preview/confirm workflow that governs any destruction, plus the important non-obvious guarantee that an old public link keeps working after a change so already-printed QR codes stay valid. It also discloses that lieu addresses are geocoded (BAN/OSM) and shown in the preview, matching openWorldHint=true.

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?

Three sentences, front-loaded with scope, then the read/write semantics, then the link-persistence caveat — every sentence conveys something operationally useful. The first sentence is dense and long, partly restating field names that the schema already lists, which keeps it just short of ideal.

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 15-parameter, no-required-parameter tool with no output schema, the description covers the critical unknowns: read vs. write mode, the mandatory preview-before-write protocol, and what changing the public link does not break. An agent has enough to call it correctly and safely without opening the schema.

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 genuine meaning beyond the schema: why panier_moyen exists (dashboard estimations), the concrete shape of the public link (stampywallet.com/rejoindre/<lien>, used by the QR) and its persistence, and the 10-lieu cap including the main address. It does not re-explain field-level constraints already carried by the schema, which is appropriate.

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?

Opens with a precise verb pair and resource ('Lit ou modifie la fiche du commerce') and then enumerates every field class it governs, so an agent knows this is the shop-profile tool, not the loyalty-card design tool. It never names a sibling (modifier_carte, voir_carte, creer_commerce) 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?

Clearly states the two operating modes: with no change parameters it returns the current fiche, with change parameters it previews by default (confirmer=false) and only writes with confirmer=true after explicit human agreement. This is actionable guidance on when to call and how, but there is no comparison to sibling tools that might also read or alter shop data.

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