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

Annotations only declare the generic mutation profile (not read-only, not destructive, not idempotent, closed world). The description goes beyond them with genuinely non-obvious behavior: tags fully REPLACES the list, due accepts 'none' to clear, and project requires a pre-existing board. The return value is also disclosed ('the task's new row'). It does not mention whether failed mid-update leaves partial state, which is the main remaining gap.

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?

Two tight sentences, front-loaded with the operation and the partial-update rule, followed by the three behaviors that would otherwise trip an agent up. Nothing is padded or repeated from the schema verbatim without added meaning.

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 9-parameter mutation with 44% schema coverage and no output schema, the description covers the highest-risk behaviors (list replacement, clearing, board precondition) and the return shape. It is short of complete because the remaining fields — especially whether 'column' implies a move and what priority/estimate do — are left entirely to a partially documented 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 description coverage is 44%, so the description should carry more weight. It reinforces the three already-documented fields (tags, due, project) but adds nothing for the undocumented ones — notes, title, column, priority, estimate_minutes — leaving roughly half the parameters with no semantics anywhere. The 'only fields you pass are touched' clause does at least explain the overall patch model across all nine.

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 ('Change a task by id') and immediately scopes it as a partial update ('only the fields you pass are touched'). It implicitly separates itself from task_move/task_add by framing 'project' as moving to an 'existing' board, but it never names a sibling, so the differentiation is inferred rather than stated.

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 partial-update line implies when to use this over a full rewrite, and 'a board that already exists' signals a precondition for the project field. There is no explicit when-not guidance or pointer to task_move, columns_set, or task_done for the cases this tool handles awkwardly (e.g. reordering within a board).

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