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

Goes well beyond the annotations: discloses that data is stored and shared with Ad Arch staff and the group office, that a confirmation email may be sent, that nothing is stored unless agreeToTerms is true or when hearing items are missing, and that a duplicate request within 24 hours returns the existing reference number. The 24-hour dedup window is a nuance against idempotentHint=false, but since calls beyond that window or with different payloads do create new records, it is not a true contradiction.

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-loads the critical usage precondition and keeps every sentence informative, but the long inline enumeration of kind values makes it a dense wall of text. The content earns its place, though the kind list could be structured more readably.

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 complex 14-parameter mutation tool with an output schema present, the description covers side effects, consent gating, validation failure behavior, dedup behavior, SLA, and the legal disclaimer (not a contract until a written quote is accepted). Nothing an agent needs to invoke it correctly is missing.

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 100%, so the baseline is 3, but the description adds real semantics: it explains each kind value (SHOOTING = filming with location and preferredDates required, MEDIA needs mediaName, CREATOR returns the registration page), and the hearing/required-items failure mode. It does not enumerate the required items for every kind, so it falls short of a 5.

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 ('Submits one request... returns a reference number and the expected response time') and immediately scopes it ('quote only is accepted'). An agent can distinguish it from the read-only sibling tools 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 a strong precondition: 'Use this only when the user has explicitly asked to request a quote or an arrangement from Ad Arch and has confirmed the details to send.' It also clarifies the CREATOR path (returns the registration page, nothing stored). It does not, however, differentiate itself from the sibling get_creator_registration_info, which appears to overlap with the CREATOR kind.

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