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

Annotations already declare readOnlyHint=true, and the description adds substantial behavioral context: ranking by weight x headroom, do_first prioritizing a band gate over points, and the fact that results are exact per-check findings. It also discloses pricing. It stops short of describing edge-case behavior or response formatting, but there is no contradiction with the read-only annotation.

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?

The description is dense but front-loaded with the core purpose, then delivers ranking logic, gate preference, alternatives, and pricing in tight sequence. It is longer than minimal, but each clause earns its place; the only minor excess is the trailing 'See apis://prices' pointer.

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?

Given there is no output schema, the description usefully summarizes what the agent will get: per-check satisfaction details, ranked facets, and a do_first headline. It also covers cost, read-only safety via annotations, and sibling routing. It would be more complete if the slug parameter were explicitly mapped to provider identity.

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?

The schema documents context fully but leaves slug as a bare string; at 50% coverage the description should compensate. The phrase 'one provider you own' implies slug identifies an owned provider, but the parameter is never named or explained directly. This adds some meaning beyond the schema but leaves the key required parameter underspecified.

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 pins the tool to a specific deliverable: 'the ranked, gated punch list for one provider you own,' with explicit contents such as agent-readiness checks and ranked Kin Score facets. It clearly differentiates from siblings like readiness_gates and simulate_fixes rather than being a generic 'fix' tool.

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?

The description explicitly routes to alternatives: 'Use readiness_gates for the gate detail and simulate_fixes to price a plan before committing to it.' It also scopes the tool to providers you own, implying it should not be used for arbitrary providers.

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