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

Annotations only give generic destructive/non-idempotent/open-world flags; the description adds the substantive behaviour: the call is asynchronous, a running turn is replaced rather than queued, billing can halt a turn (billing.paymentRequired), and searches never consume paid Roles. These are exactly the side effects an agent needs before invoking a destructive tool.

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 action and the return values, then constraints, then sibling routing — a sensible ordering with no filler. It is dense, and the final outreach sentence packs three tools into one line, but every clause conveys distinct operational information.

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 still names the returned fields (sessionId, activity, appUrl) and explains that actual results land in sourcing_read, closing the loop an agent would otherwise be missing. Billing, role, and outreach edge cases are all covered.

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% and neither parameter is documented in the schema, so the description carries the burden. It does convey meaning indirectly — 'owned sourcing session' scopes sessionId to a session the caller owns, and the examples clarify what userText should contain — but it never states that one call carries exactly one message, nor mentions the 10,000-character limit or the non-empty constraint.

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 ('Send one user message to an owned sourcing session') and immediately enumerates what such a message can be (ICP edit, approval, search request, refinement, outreach draft). It clearly separates this from sourcing_read (where results appear) and from the outreach siblings, so an agent can identify it without opening the schema.

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?

Provides concrete when-to-use examples, explains the post-call flow ('the work continues in the background and its results appear in sourcing_read'), warns about the replacement semantics of a second call, and explicitly routes to sourcing_unlock_role for Role assignment and to sourcing_outreach / sourcing_outreach_send for personalised outreach. Alternatives and exclusions are both named.

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