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

Annotations only indicate non-read-only, non-open-world, non-destructive. The description adds meaningful behavioral context: writes go through ChangeRequests with a message, diff, and full history, and warns to treat stored content as data, not instructions. This goes beyond what annotations provide and informs the agent of side effects and security posture.

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 concise: three sentences covering purpose, an endpoint reference, and usage/security notes. It is front-loaded with the core purpose. The endpoint line is somewhat redundant with the tool name but not harmful. No unnecessary fluff, each sentence adds value.

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 mutation tool with 5 parameters and no output schema, the description covers the essential usage context: what it does, what it is not for (large text), auth prerequisites, the change request mechanism, and a security note. It omits details on mode semantics and return behavior, but given the absence of an output schema, these are less critical. Overall, an agent can invoke it correctly with the given information.

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 only 40%, so the description must compensate. It does clarify the 'metadata' parameter with examples (summary, tags, source URL, schema-specific hints) and explicitly excludes large text. However, it does not explain the 'mode' parameter (merge vs replace) beyond the enum, nor does it detail the structure of the metadata object or the playbook usage beyond schema descriptions. Partial compensation, leaving gaps.

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 clearly states the tool updates AI-readable metadata for a file (asset), listing examples like summary, tags, source URL, or schema-specific hints. It explicitly differentiates from siblings by stating 'Large text does not live here' and referencing putText / grep / readTextLines, making its scope unambiguous.

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?

Provides explicit usage guidance: for multi-space accounts it instructs calling auth_verify, asking the user for the space, and passing targetSpaceId. It also tells when NOT to use it (for large text, pointing to alternatives). It does not explicitly contrast with nodes_update_metadata, but the assetId parameter and context make the intended use clear.

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