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

The description discloses important behavioral details beyond the annotations: deletion is a reversible archive ('archived=true hides the task but keeps it'), archived=false restores it, and the return value matches a query_crm_tasks row. It also warns about the follow-up suggestions limitation, giving the agent accurate side-effect expectations.

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 summary is a compact paragraph that front-loads the verb and action list, then adds only high-value caveats: id source, reversible delete behavior, and the follow-up limitation. The returns block is minimal and useful. There is no filler or repetition.

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 12-parameter mutation tool with no output schema, the description plus schema covers everything an agent needs: supported operations, id source, soft-delete behavior, return shape, and an explicit limitation. It is complete enough to invoke correctly.

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 100%, and each parameter already has rich descriptions, such as notes vs notes_append, archived semantics, and assignee_email sourcing. The description's summary does not add per-parameter detail, but that is unnecessary given the schema's completeness, so the baseline 3 applies.

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 'Change a CRM task' and enumerates the full set of supported operations: mark done/reopen, reschedule, rename, reassign, edit notes/links, and delete/restore. This makes the tool's scope unambiguous and clearly distinguishes it from siblings like create_crm_task and query_crm_tasks.

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 explicitly tells the agent to get the id from query_crm_tasks and states a clear when-not: follow-up suggestions the user hasn't added cannot be changed here. It does not explicitly name alternative tools such as create_crm_task for creation, but the context is still sufficient for correct usage.

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