find_duplicates

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context beyond that — that resolving duplicates is the person's call via mark_job, and that get_job surfaces duplicate_of for one job — but says little about ordering guarantees or output volume beyond the field list.

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?

It is a single run-on paragraph mixing the definition, the strong/maybe distinction, output shape, and sibling references. Content is relevant but not front-loaded or structured, making it harder to parse than it needs to be.

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?

An output schema exists, so return values need not be spelled out, yet the description still sketches the per-pair payload (why, strong, both jobs with key/company/title/status/date/closed). Combined with the strong/maybe distinction and the mark_job handoff, an agent has what it needs to call this correctly.

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 baseline is 3, but the description meaningfully elaborates the single parameter by defining what 'strong' means (a shared req or posting id) versus 'same title alone', which is exactly what strong_only filters.

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 states a specific outcome: pairs of tracked jobs that are the same opening, with a distinction between 'strong' (shared req/posting id) and 'maybe' (same title) matches. It is distinguishable from siblings like get_job or check_postings, though it opens with a dense clause rather than a crisp verb+resource statement.

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?

Usage is implied rather than spelled out: it notes 'the person decides what to skip (mark_job)' and that get_job's duplicate_of covers a single job, which hints at when to use this vs get_job. But there is no explicit when-to-use/when-not statement or prerequisites for invoking it.

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