careers_check_search

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

The description goes well beyond the annotations by detailing side effects: default is preview/no-write, advance_baseline commits private local state only after a complete scan, first scan marks all matches added, and truncated output is not the full change list. It also warns to persist returned changes before committing. No contradiction with readOnlyHint=false, idempotentHint=false, or destructiveHint=false.

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?

Every sentence carries operational weight: the core function, default safety, baseline flags, first-scan behavior, notification guarantee, and persistence caveat. It is dense but well-front-loaded and not bloated.

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 tool with stateful baseline behavior and potential truncation, the description covers the critical decision points: preview vs. commit, when to reset, first-scan behavior, no notifications, and reliability guidance for downstream consumers. The output schema exists, so return-value documentation is not the description's job.

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 0%, so the description must compensate. It explains advance_baseline and reset_baseline well, and the truncation warning indirectly relates to max_items. However, the required 'name' parameter is not semantically explained at all, and max_items is never explicitly linked to output size, leaving an agent to guess what value to provide.

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?

The description opens with a specific verb and resource: 'One-shot complete search diff: new, changed and no-longer-matching jobs.' This clearly distinguishes the tool from siblings like careers_searches and careers_jobs by framing it as a diff operation rather than a plain listing or save action.

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?

It explains exactly when to use the default preview vs. advance_baseline=true, and when reset_baseline is appropriate ('explicitly changed query/account'). It also states what the tool never does ('Never schedules or sends notifications'), helping an agent choose it only for diffing, not for notification workflows.

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