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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's extra context is what counts here: the consent gate, the guarantee that only user-authorized fields are shared, and the fact that it returns a referral id plus a private status token. That is meaningful disclosure beyond the annotations, though it says nothing about failure modes, duplicate handling, or delivery latency.

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?

Four short sentences, zero waste, with the consent precondition front-loaded and the return value disclosed at the end. Every sentence carries information the agent needs.

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 11-parameter write tool with a nested consent object and no output schema, the description covers the highest-risk aspects (consent gating, authorized-field sharing, return shape) but leaves most parameter semantics undocumented. Adequate for safe invocation, incomplete for correct invocation.

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 only 36% across 11 parameters, so the description must compensate and largely does not. It touches only the consent concept ('shares only the fields the user authorized'), leaving state, contact, match_id, practice_area, preferred_contact_method, attribution_token, and idempotency_key unexplained in both schema and description.

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 ('Record a client-authorized introduction to ONE lawyer'), which is distinguishable from discovery siblings like find_attorneys and get_referral_status. It does not name a sibling explicitly, so it falls short of the 5 bar, but the purpose is unambiguous.

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 an explicit precondition: call only after the user has seen the lawyer's name, the exact details to be shared, and explicitly agreed. That is strong when-to-call guidance. It stops short of a 5 because it names no alternative tool (e.g., use find_attorneys to obtain attorney_id first) or when-not-to-call condition.

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