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

No annotations are provided, so the description carries the full disclosure burden. It usefully reveals the cursor/pagination model and that results are an append-only event stream, but says nothing about retention window, event ordering, limits on the feed, or permissions. Partial behavioral context for a read tool.

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, no filler. The resource identity is front-loaded and the cursor mechanic follows immediately. 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?

With no annotations, no output schema, and 0% parameter coverage, the definition leaves notable gaps: what an event object contains, how limit and types behave, and any retention or ordering guarantees. The core purpose and pagination are covered, which is the minimum viable level.

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 compensate. It explains since_id's real semantics (resume cursor sourced from a prior last_id), which is genuine value beyond the bare integer schema, but limit and types are left completely unexplained.

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+resource (event feed) and grounds it with concrete example event types (job.completed, pipeline.completed, veille.run_completed), which makes the resource scope unambiguous. It does not explicitly contrast itself with siblings like get_job or list_jobs, but the 'feed' framing is distinct enough that an agent can separate it.

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?

The cursor instruction ('pass back last_id as since_id') gives clear operational guidance for continuing a feed, but there is no statement of when to use this tool rather than list_jobs or get_job, nor any exclusions. Usage is implied by polling semantics rather than stated.

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