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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds useful context the annotations don't carry: coverage across every job board in the directory and the incremental daily-read pattern that makes the tool cheap. It says nothing about default limit, ordering, or what board_gone means, which are behavioral traits an agent would otherwise have to guess.

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 sentences, front-loaded with what the tool returns, then the polling instruction, then filtering. No filler and no repetition of schema or annotation content.

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 7-parameter, unrequired, read-only feed with no output schema, the description covers what is returned and how to schedule calls, which is what an agent most needs. Gaps remain around result ordering, the default limit, and the meaning of the board_gone change kind, but they are secondary rather than blocking.

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 goes slightly beyond the schema by explaining since as 'the last day you saw' (stateful semantics, not just a format) and by clarifying that omitting companies means the whole market. It leaves kinds values and offset paging to the schema, which is the right division of labor.

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-and-resource: a day-by-day change feed of job postings (new, removed, reopened, edited) pulled from every board in the directory. That is far more than a restatement of the title. It does not name or contrast a sibling, so an agent must infer that list_open_jobs is the snapshot alternative rather than having that spelled out.

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 concrete usage guidance: call each day with since set to the last day seen instead of re-reading every board, a clear incremental-polling workflow. It also explains when to omit companies (whole market) versus filtering by kind and title words. It stops short of explicitly naming an alternative tool for the case where the agent needs the current open-jobs snapshot.

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