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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with 'nothing is stored, so tell the user to save the summary' and 'Returns a plan_id'. It additionally discloses widget-mode behavior (keep replies short, don't repeat the card) and the anti-hallucination rule ('must come from the user... never guess'), which annotations cannot express.

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 purpose and use condition, and nearly every clause adds operational detail. There is mild redundancy: the 'use when the user is unsure...' framing is restated later as 'Use when someone asks how to know if they're ready for a breed', which could be merged.

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 12-parameter tool with no output schema, the description covers everything an agent needs: required user-supplied inputs, what the plan contains, the plan_id return, storage semantics, and widget display behavior. Nothing material is left for the agent to infer.

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 100% and includes enums for 11 of 12 params, so the baseline is 3. The description adds genuine meaning by naming the five key answers that must come from the user (home, activity, experience, kids, time alone) and by tying trial content to inputs like coat care, noise, floor space and the vet-cost budget, exceeding what the schema alone conveys.

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 artifact ('Builds a short, practical try-before-you-adopt plan (3, 7 or 14 days) for ONE named breed') and enumerates the concrete contents of the plan. It is clearly distinguishable from siblings like assess_breed_fit (which evaluates fit) and review_test_drive (which reviews an existing plan).

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 triggering conditions ('when the user is unsure whether they are ready for a specific breed', 'wants to try before buying') and explicit exclusions ('Do not use for symptoms, emergencies or treatment questions... or for training and behavior how-tos'), redirecting symptom questions to a veterinarian. It also captures a behavioral nuance: if the eight weeks... rather, if several of the five key answers are missing, ask for them in one message and reuse prior answers.

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