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

With no annotations, the description carries the full behavioral burden and does so impressively. It discloses that the whole body is replaced, the previous body is kept as a version, credentials are refused, bearer token auth is required, and editor access is needed for shared brains.

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?

Four dense sentences, each earning its place: purpose, default targeting and permissions, replacement/append semantics, and security. No filler or redundancy, and the most important behavioral information is front-loaded.

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 write tool with no output schema, the description is complete: target selection, access prerequisites, mode behavior, versioning, and auth are all covered. An agent has enough to invoke the tool correctly without needing to open the schema.

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 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: the default-brain behavior when 'brain' is omitted, the access requirement for shared brains, and the version-retention consequence of replace mode. This goes beyond simple restatement.

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 opens with a specific verb-resource pair, 'Create or update a Brain file,' which clearly identifies the tool's function. It is immediately distinguishable from the read/search siblings like brain_get, brain_list, and brain_search.

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?

The description provides clear usage context: writes to the default brain unless another is named, shared brains need editor access, and mode 'append' adds to the end while the default replaces. It doesn't explicitly contrast against read tools or say when not to use it, but the sibling names make the primary distinction obvious.

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