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

Annotations already establish that this is a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower, and the description still adds real behavior: it watches roughly every minute and does not backfill historical data ('sans reprise des données anciennes'), plus the connection/activation prerequisites. It does not explain the shape of the returned check/error payload, which matters somewhat since there is no output schema.

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 short sentences, no filler, with the core purpose stated first and prerequisites and cadence following. Every sentence carries distinct information.

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?

The behavioral side is well covered for a read-only, no-output-schema tool (prerequisites, cadence, no backfill). The definition is still incomplete on the one input it requires, leaving the identity of 'id' undefined, which could cause a mis-invocation. The description is also written in French while the surrounding tool surface is English.

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?

There is one required parameter, 'id', with 0% schema description coverage, and the description never mentions it. The agent cannot tell from either source whether this id is a workflow id, a connection id, or a watch id. Since coverage is below 50%, the description was expected to compensate and does not.

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 resource and result: the last check and error of an application trigger ('Dernière vérification et erreur d'un déclencheur d'application'), which lets an agent distinguish it from generic workflow tools like describe_workflows or run_flow. It does not, however, differentiate itself from near siblings such as get_workflow_communication, list_workflow_app_connections, or workflow_history.

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 states two concrete preconditions for use: a connection must be selected and the workflow must be activated ('Une connexion doit être choisie et le workflow activé'). It also sets expectations about polling cadence. It stops short of naming an alternative tool or stating when not to use it.

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