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

Beyond the annotations (destructiveHint=true, openWorldHint=true, idempotentHint=true) the description discloses the two behaviors that matter most: the call consumes Margo credits and should not be fired without user agreement, and requestId is the idempotency key that must be reused on retries. It also warns that missing contacts and partial or empty results are possible, which sets correct expectations for an expensive open-world operation.

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?

Dense and front-loaded: the action, the credit cost, the idempotency rule, and the return value arrive in the first four sentences with no filler. Later sentences on geography and partial results are terser and slightly telegraphic, but nothing is padding.

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 an 18-parameter, nested-schema, no-output-schema tool this is only partially complete. The critical operational context (cost, idempotency, jobId handoff, unreliable results) is present, but most filter parameters carry no meaning in prose and the shape of the eventual result beyond a jobId is not described.

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 description coverage is 0% across 18 parameters (including the nested linkedinParams object), so the description has to carry the load. It does explain requestId, maxCredits, and the country/city targeting difference between sources, which is high-value. But source enums, geographyPolicy, requiredChannels, decisionMakerTitles, the rating filters, and the whole linkedinParams sub-object are left entirely to bare schema names.

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: "Create or resume one durable prospect search." That clearly separates it from get_search_status (polling) and points to asynchronous job semantics. It stops short of distinguishing itself from the pipeline siblings (prepare_pipeline, run_pipeline_sample), so an agent must still infer whether a search job or a pipeline run is the right path.

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 gives a concrete prerequisite sequence — check capabilities and usage, agree the credit cost with the user before calling — which effectively routes the agent to get_margo_capabilities and get_usage_and_quota. It also names get_search_status as the follow-up. It does not state when NOT to use this tool versus the pipeline or read_pipeline_leads siblings, so guidance is strong but incomplete.

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