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

The annotations already mark this as read-only and non-destructive, and the description adds substantial behavioral detail beyond that: locale affects the rendered footer, 404 occurs on missing node/prompt/access, stored text is untrusted, and the tool never authorizes approving or merging a change request. No contradiction with annotations.

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 well organized: it front-loads the core output, then handles each kind, then covers errors, auth, and trust. The final Busabase/ChangeRequests sentence is slightly tangential to this specific call, but it supports the security guidance and does not feel padded.

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?

There is no output schema, so the description carries the burden of explaining return content, and it does: rendered prompt body for 'prompt', SKILL.md plus file list for 'skill', and pointers for reading additional files. It also covers locale behavior, error conditions, multi-space authentication, and trust boundaries, making the tool safe and correct to invoke.

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 schema description coverage at 60%, the description compensates for key, kind, locale, and targetSpaceId by explaining where values come from and how they affect the rendered output. Only nodeId receives no added semantic explanation, which is a minor gap since it is a required path parameter.

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 specific resource (one playbook) and distinguishes its two forms: a rendered custom prompt for kind 'prompt' and a SKILL.md plus file list for kind 'skill'. It also differentiates itself from siblings by referencing playbooks.search for keys and node_file_read for further skill files.

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 clear usage context: pass a key from playbooks.search, read further skill files with the appropriate file-read call, and call auth_verify before choosing a targetSpaceId in multi-space accounts. It does not state explicit 'do not use when...' exclusions, but the routing guidance is strong enough to guide tool selection.

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