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

Goes well beyond the annotations by disclosing the async contract: it returns sessionId/activity/appUrl as soon as the turn is accepted and the work continues in the background. It also discloses the billing behavior (searches never assign a paid Role, evaluation halts with billing.paymentRequired) — important context given destructiveHint=true and no output schema. It does not clarify that repeat calls create new sessions (idempotentHint=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?

Front-loaded with the core action and the mode distinction, then the async/return contract, then the billing caveat. Dense but every clause carries information; the billing sentence is long and could be trimmed, but it prevents a costly misinterpretation.

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?

With no output schema, the description supplies the return shape (sessionId, activity, appUrl) and explains where the real results land (sourcing_read). Combined with the async and payment-required disclosures, an agent has everything needed to call this and interpret the immediate response.

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%, so the description must carry parameter meaning. It fully explains startMode including which value is the default, but the required `prompt` parameter is only obliquely implied by "from a hiring brief" — no guidance on what the prompt should contain, its structure, or the 10000-character limit.

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: "Create a sourcing session from a hiring brief and start its first turn." It then differentiates the two startMode behaviors and names the downstream siblings (sourcing_read, sourcing_unlock_role) so the agent knows exactly what this tool does versus what happens later.

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?

Explicitly explains which startMode to pick ("review_criteria" default drafts an ICP for review; "find_candidates" searches immediately), which is real routing guidance. It also directs the agent to sourcing_read for results and sourcing_unlock_role for Role assignment, though it never states when NOT to call this (e.g., when a session already exists and sourcing_continue should be used instead).

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