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

Annotations declare readOnly/openWorld=false/destructive=false, and the description still adds non-obvious behavior: a 404 when node, prompt key, or read access is missing, locale-dependent rendering with an English/footer fallback, and a security instruction that stored text is untrusted and never authorises approving or merging a change request. These go well beyond the structured annotation 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?

Dense and front-loaded, with the return location (`content`) stated first and the multi-space/auth guidance kept to a final paragraph. There is mild redundancy: the locale footer behaviour is explained in both the description and the `locale` schema field, though the description version adds the fallback case.

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?

No output schema exists, yet the description explains the returned content for both kinds (rendered body vs SKILL.md plus file list), the error condition, and the multi-space path. Nothing essential for a correct call 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?

With only 60% schema coverage, the description compensates: `key` is required only for prompts and comes from `playbooks.search`, `nodeId` accepts an id or a slug, and `locale` controls the rendered body and footer wording. It adds semantics the schema does not state.

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+resource (fetch a playbook) and immediately splits it into the two distinguishable return shapes, `kind: "prompt"` (rendered prompt body) and `kind: "skill"` (SKILL.md text plus file list). An agent can tell exactly what comes back and how the two kinds differ.

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?

Explicitly routes: pass `key` from `playbooks.search` for prompts, read further skill files via the surface-specific call (CLI `skills read-file`, MCP `node_file_read`), and for multi-space accounts call `auth_verify` and ask the user before passing `targetSpaceId`. Alternatives and preconditions are named, not implied.

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