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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds real value on top: the optimistic-concurrency contract, where to obtain the version, and what a stale version produces. It does not clarify whether omitted fields are left untouched or that null clears due_date/description, which is the one behavioral gap left for a destructive mutation.

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?

Three sentences, each doing distinct work: scope of editable fields first, then the required precondition and its failure mode, then the sibling redirect. No filler and no repetition of schema constraints.

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?

An output schema exists so return values need not be described, and the mutation's risk profile plus concurrency requirements are covered. Missing only the partial-update and null-clearing semantics, which matter for a destructiveHint mutation but are modest gaps given the rest of the coverage.

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?

With 0% schema description coverage, the description must carry meaning, and it explains the hardest parameter (expected_version: required, sourced from list_tasks, conflict on mismatch) and enumerates the mutable fields mapping to six of the eight parameters. It leaves the null-vs-omit distinction for due_date and description, and the 'non-terminal status' constraint restates what the enum already shows.

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 (update) plus the exact updatable fields (title, description, priority, due_date, responsible member, non-terminal status), which maps directly onto the schema's editable properties. It also explicitly separates itself from complete_task, so an agent can distinguish it from the closest sibling 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?

Gives an explicit precondition (expected_version is required and must come from list_tasks), explains the failure mode (mismatch returns a conflict with the current version), and names the alternative tool for the out-of-scope case (finishing a task -> complete_task). All three routing decisions an agent must make are covered.

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