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

Adds real context beyond the annotations: the operation is asynchronous and returns emailLookupStatus, it calls an external enrichment provider, and results remain subject to the session's masking. It does not explain why destructiveHint=true is set — e.g. credit consumption or overwriting an existing email — which is the one behavioral fact an agent most needs before invoking.

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 tight sentences, front-loaded with the action and immediately followed by what it returns and what happens next. No filler.

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?

Covers the async lifecycle, return value, provider dependency, and masking constraint — enough to invoke correctly without an output schema. Minor gaps remain around failure modes and cost/side-effect of the destructive hint.

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 carry the load. It implies the two parameters through 'one candidate in an owned sourcing session,' but gives no format, ownership prerequisite, or ID-source guidance for sessionId and candidateId.

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 (start a work-email lookup) and resource (one candidate's work email) scoped to an owned sourcing session. It also implicitly separates itself from sourcing_read by making clear that tool is where the result surfaces, not where the lookup is triggered.

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 clear context: use this when you need to enrich a single candidate's work email, and the result will appear via sourcing_read later. It lacks explicit exclusions — e.g. whether to avoid calling when a lookup is already pending, or whether it can be re-run for the same candidate.

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