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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known. The description adds non-obvious context the annotations don't: the pending-only state constraint, immediate execution, and tenant isolation. It stops short of describing what a cancelled task's downstream effect is (e.g., whether resources are released or errors occur).

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 purpose, then behavior, then the required-parameter/example block. Nearly every sentence earns its place; the one marginal element is 'Mirror of Meta MCP tasks_cancel', an internal-implementation note with little selection 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 a destructive annotation and no output schema, the definition covers state preconditions, immediacy, isolation, and the required argument with an example. The only missing piece is documentation of the connection_context parameter.

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 description coverage is 0%, so the description carries the burden. It documents task_id as a required UUID string and supplies an example call, but says nothing about the second parameter (connection_context) or its mctx_v1_ pattern. It compensates for the most important parameter but leaves a gap.

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 and resource ('Cancel one pending task') and scopes ownership ('owned by the current user'). This clearly distinguishes it from sibling read tools like tasks_list, tasks_get_status, and tasks_latest without needing the 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?

Provides a real when-not rule: 'Only tasks in `pending` state can be cancelled (already-running tasks must complete on their own).' It also flags immediacy ('call is IMMEDIATE'), which governs how an agent should sequence the call. It does not name an alternative tool for non-pending tasks, but no sibling appears to serve that case.

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