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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, but the description adds real behavioral context: accounting entries are created as a side effect, no message goes to the tenant, and behavior matches the web app. It stops short of saying what happens on a repeat call even though idempotentHint=false, so the duplicate/error path stays unstated.

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?

One compact block, front-loaded with the triggering condition, then the effect, then the exclusion. Every clause carries information; 'like the web app' is the only slightly soft phrase but it usefully anchors expected behavior.

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 4-parameter mutation with no output schema, the description covers the trigger, the side effects, the non-effect (no tenant notification) and the per-month uniqueness rule. The main gap is the consequence of calling it twice for the same lease/month, which matters given idempotentHint=false.

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 only 25% (only 'abonne' is documented), so the description carries more burden. 'One call per lease and month' does usefully imply that bail_id + annee + mois form a uniqueness key, but it adds nothing on formats (e.g. whether annee is 4-digit) or on the admin-key requirement for 'abonne'.

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 names a specific verb and resource ('records the rent call (avis d'échéance) in the account, with its accounting entries') and explicitly separates it from the sibling that notifies the tenant (immo_avis_echeance_envoyer). An agent can distinguish create-vs-send without consulting either schema.

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 opens with an explicit trigger condition ('WHEN the rent of a month must be called for a lease') and names the alternative tool for the adjacent intent ('Nothing is sent to the tenant (see immo_avis_echeance_envoyer)'). The exclusion plus the pointer to the sibling leaves little to inference.

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