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

With only destructiveHint=true in annotations, the description adds real behavioral value: it declares this is a mutation, names the exact GraphQL operation, discloses the required write scope (TASKS_WRITE), and warns that `content` must be a stringified TipTap/ProseMirror document. It omits return shape, idempotency, and how `fields` interacts with the typed 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?

Front-loads the mutation warning and required inputs, then moves to optional links and the permission requirement. Dense but every sentence contributes; the GraphQL signature line is slightly redundant with the schema but useful for agents familiar with Parabol.

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 10-parameter mutation with a nested free-form `fields` object and no output schema, it covers required fields, optional relationships, content format, and auth scope. The gap is the verbatim-merge escape hatch in `fields`, which is undeclared in the description.

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, but the description goes further by flagging which params are required, spelling out the status enum, and explaining the plaintextContent-vs-content distinction. It still doesn't explain the `fields` override or `sortOrder`.

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?

Opens with an explicit verb+resource+scope: 'MUTATES Parabol data: create a task on a team', and names the underlying mutation createTask(newTask, area). An agent can distinguish it from update_task and list_tasks without opening either 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?

It states the required inputs (teamId, status with its enum values) and gives positive guidance on the content fields (use plaintextContent for text, and/or content as stringified TipTap/ProseMirror JSON). It also names the TASKS_WRITE prerequisite. It does not explicitly contrast with update_task or add_comment, so it stops short of full when/when-not routing.

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