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

Adds substantial context beyond the annotations: it discloses that accepting this creates an external, non-idempotent request that a partner lawyer will act on and follow up by phone/e-mail, enumerates the consent preconditions, and forbids fabricating contact details. Annotations only say openWorld=true and non-idempotent; the description explains what that actually means for the user's privacy and follow-up.

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 purpose, then the gating conditions, then content guidance, then the return value. Every clause carries a distinct instruction (consent gate, phrasing rule, anti-test warning, return value) with 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?

For a 16-parameter submission tool with 94% schema coverage, the description covers the risky parts well: consent, contact integrity, phrasing, and the returned request number (important since there is no output schema). It leaves optional-parameter selection entirely to the schema, which is acceptable but leaves a small gap around when budget/deadline/documents matter.

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 94%, so the baseline is 3, but the description adds real meaning: how the task text should be phrased (situation, goal, key facts in the user's own terms) and an integrity rule for the contact fields ('never invent contacts'). It does not explain any of the 12 optional fields, which the schema already handles.

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, resource and outcome: send the user's legal task to Pactum lawyers, who review it and contact the user with a price. That is clearly distinguishable from the sibling read/search tools (get_service, list_practice_areas, search_articles, search_services) without opening any 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?

Gives explicit preconditions (call ONLY after the user asked to be contacted, gave real name and phone/e-mail, and consented to storage and partner-lawyer sharing) plus a clear prohibition ('never call it "to test"'). It stops short of routing the agent through the sibling discovery tools (search_services, list_practice_areas) before submitting, which is implied only via the schema's service_slug/practice_area descriptions.

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