App recipe

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

Annotations already carry readOnlyHint/idempotentHint, so 'Read-only' is largely redundant, but the description adds real behavioral weight: it defines the full state vocabulary (ok | drift | unknown | not_connected | error) and explicitly warns that 'unknown' never means healthy and 'not_connected' means nothing is configured. That prevents an agent from misreading results. It stops short of auth/rate-limit or pagination behavior.

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 purpose, then the element set, the state vocabulary, the return shape, and finally alternatives — each block serves a distinct need. The inline return-shape JSON is the heaviest part but is justified because there is no output schema. Slightly dense rather than wasteful.

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 no output schema, the description takes on the return-value burden itself and lists the full response shape ({ projectId, worst, elements, manifest, snapshotHash }) plus the element state semantics. For a single-param read tool this covers everything an agent needs to call and interpret it.

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?

Only one parameter with 100% schema description coverage; the schema already documents projectId, its UUID type, the server-configured default, and the `project_id` alias. The description adds nothing beyond it, so baseline 3 applies.

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?

Specific verb+resource ('Return the App Recipe for a project') with the exact contents enumerated (per-element cards for schema, design, routes, gates, ci, deploy, env, integrations). It also names the sibling tools it is not (get_design_tokens, get_design_deviance, list_gate_findings), so an agent can route 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?

'Use to see how the app is put together and which part is drifting' gives the selecting condition, and it explicitly routes to get_design_tokens for token values, get_design_deviance for code that drifts off them, and list_gate_findings for gate detail. When-to-use and alternatives are both explicit.

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