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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the cursor/pagination behavior, which is real value, but omits ordering (newest first?), retention window, and whether events are filtered by account scope or polling frequency.

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 compact sentences with no filler; the core purpose is front-loaded and the pagination rule is tacked on as a practical afterthought. Every clause earns its place.

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 no-required-param, read-only feed with no output schema, the description covers the essentials, but an agent still lacks guidance on result shape (beyond the event-name examples) and the semantics of 'limit'/'types'. Adequate but with clear gaps.

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 0% across three parameters, so the description must carry the load. It explains since_id well and the event-type examples hint at what 'types' accepts, but 'limit' (max 100) and the exact accepted values for 'types' remain undocumented.

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 resource ('Account event feed') with concrete example event names (job.completed, pipeline.completed, veille.run_completed), which lets an agent recognize it as an event stream distinct from the job/pipeline CRUD siblings. It does not explicitly name a sibling it differs from, so it falls short of a 5.

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?

Gives operational guidance for pagination ('since_id takes the last_id of the previous call'), which is genuinely useful for iterating the feed. However, it never states when to use this versus alternatives like list_jobs or get_job, nor when not to use it, so usage is only implied.

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