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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds behavior beyond that: the shape of the output artifacts, the mode switch on churn_reasons, and the fact that optional interventions and data signals are consumed when supplied. It does not mention response length, latency, or how the sector inference fallback is signaled beyond 'names what it read' in the schema.

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?

Three sentences, front-loaded with the purpose, then the fallback mode, then optional-input behavior. Every sentence carries new information and none restates the title. The sentences are long and clause-heavy, which slightly hurts scannability but not substance.

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 10 parameters and no output schema, the description must explain what comes back — and it does, listing health signals, interventions and an email draft per reason, plus the discovery-kit variant. Required vs optional inputs are handled by the schema. Minor gaps: nothing about output volume or how the two modes differ in size, but nothing an agent needs in order to call 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 description coverage is 100% and four parameters carry enums, so the schema does most of the work and the baseline of 3 applies. The description does add genuine semantics for churn_reasons (blank triggers the discovery-kit branch) and for current_interventions (compared against the playbook). It says nothing about the near-duplicate industry vs your_sector distinction, leaving that entirely to the schema.

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?

The description names a concrete deliverable — a retention playbook containing health signals, interventions and an email draft per churn reason — plus a second output mode (churn discovery kit). That is far more specific than the title 'Retention Playbook'. It never contrasts itself with any sibling tool, though the sibling set (pmf_scorecard, competitive_intel, crisis_planner) is topically distinct enough that confusion is unlikely.

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?

Explicit conditional routing is given: 'If you do not know why customers leave, leave the churn reasons out and you get a churn discovery kit instead.' That tells the agent when to omit an input and what changes as a result. It stops short of naming an alternative tool for adjacent jobs (e.g. PMF scoring or customer interviews), so no true alternatives guidance.

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