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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuine context beyond that: it discloses the shape of the returned data (change events with before/after and timestamps plus a current snapshot) and an auth prerequisite (the edm_… token).

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?

Two short sentences, front-loaded with what the tool returns before the auth note. Almost no waste; the parenthetical efficiently conveys the event structure.

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 returns, and it does so reasonably by describing the change-event shape and the snapshot. Combined with full schema coverage and complete annotations, an agent has enough to call it correctly; only pagination/result-size behavior is 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 both the required 'id' and the 'limite' range are already documented in the schema. The description adds no parameter-level detail (no mention of id semantics or the 1-100 limit), so baseline 3 applies.

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 (list) and resource (events of a watched procurement), and disambiguates the resource by unpacking what an 'event' actually is: what changed, from what to what, and when, plus the current snapshot. It is clearly distinguishable from watch_procurement, though it never names the sibling explicitly.

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?

Usage is only implied: the mention of 'a watched procurement' signals it is meant to be called after watch_procurement, but there is no explicit when-to-use, when-not, or alternative routing (e.g. vs list_alert_matches or get_procurement). Adequate but leaves selection to inference.

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