Poll for new & changed job requests (sync feed)

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

Annotations already declare readOnlyHint=true, but the description adds materially beyond that: the server primes the cursor at 'now' on first poll, re-scans a ~5s safety window causing duplicate deliveries, orders results by updated_at ASC, and includes soft-delete/archive changes. No contradiction with annotations.

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?

The description is long but every sentence is load-bearing: it teaches a stateful protocol that is easy to get wrong. The content is front-loaded with the core concept, then organized as a numbered how-to, with the important caveat ('never blindly append') placed inline. No fluff.

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?

Despite having no output schema, the description fully specifies return mechanics (next_since, has_more, item ordering, duplicate re-delivery) and usage lifecycle. For a stateful sync-feed tool this is exactly the information an agent needs to call it correctly without guessing.

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 100%, so the baseline is 3; the description earns an extra point by explaining cursor lifecycle (omit `since` to prime, use `next_since` from the response), `limit`/`has_more` interaction, and how filters narrow the feed. It doesn't enumerate each filter parameter, but the schema already documents those adequately.

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 ('Poll'), resource ('job requests'), and the distinguishing property ('new & changed', sync feed). It explicitly contrasts with paginated listing, and the title reinforces the purpose. An agent can tell it apart from listJobRequests without opening the 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?

Provides a numbered usage protocol: omit `since` on first poll, store `next_since`, pass it back, upsert on `id`, and re-poll when `has_more` is true. It also tells the agent when NOT to use it ('This is NOT pagination') and directs the initial bulk load to GET /job-requests.

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