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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds real behavioral value: the conditional return shape for recipes with vs. without a build path, and the directive to inspect packet_kind/next_step. It also discloses data-handling/telemetry scope (what is stored, hashed, or never collected), which is beyond structured fields.

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 trigger condition is usefully front-loaded, but the body is a long run-on clause chain and the trailing privacy/telemetry boilerplate is lengthy relative to selection value. Several sentences do not help an agent choose or invoke the tool.

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 read-only single-parameter tool with no output schema, the description adequately explains what comes back and the two return modes, so an agent knows what to expect. The remaining gap is how to source a valid recipe_id, which is left implicit.

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 0% and there is no description of recipe_id anywhere — no format, no explanation of where to obtain it (e.g., from search_recipes or get_recipe). With one undocumented parameter, the description fails to compensate for the schema gap, so it falls below the 3 baseline.

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 states a specific verb and resource: it returns SPEC.md, AGENTS.md and runbook files for a recipe with a build path, and clarifies the fallback case (assessment files for switch/downgrade validation). The core purpose is clear, though it is wrapped in a dense run-on sentence and the odd 'Replace with AI' phrasing; it also does not name a sibling to contrast against.

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?

It gives an explicit trigger condition ('Use when the user wants to replace a tool by building their own') and a handling instruction ('Check packet_kind and next_step before acting'). It does not name alternatives among siblings such as get_recipe or get_exit_plan, so routing is only partially resolved.

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