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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing the REST equivalence ("mirrors REST GET /v1/tasks") and, importantly, the detail-level contract — which fields come back at summary vs standard/full — which materially affects how the agent should call it. It omits pagination/limit behavior and result ordering.

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-loaded with the verb, then a dense filter glossary, then the detail contract, then a provenance line — every fragment maps to a parameter or a behavior. The telegraphic style with semicolons is efficient but slightly hard to scan; it is not padded.

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 shape need not be restated, and the detail-level mapping is a welcome bonus. Against a 12-parameter tool with zero schema descriptions, though, four parameters (kind, namespace, assigned_role, required_role) and the limit default/max are undocumented anywhere, so an agent cannot reason about the role-matching filters that the description itself alludes to.

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 the load, and it does for the highest-value filters: it explains the semantics of claimable_by_me, assignee="me", parent, task_key (comma-separated keys or ids), diagram_key (chunk tasks, combine with claimable_by_me), status (comma-separated list), and detail. It leaves kind, namespace, assigned_role, required_role, and limit wholly unexplained, which is a real gap at 12 parameters.

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?

"List tasks" is a specific verb+resource, and the following clauses make the scope of the listing concrete (claimable, by assignee, by parent, by key set, by diagram, by status). It never distinguishes this from siblings such as get_task_tree or get_task_tree-adjacent readers, so an agent must infer that this is the flat list and the others are tree/relationship views.

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 description gives per-filter guidance in a usage register, e.g. "claimable_by_me=true: what you may claim now (role, assignee, capabilities)" and "diagram_key: ... (combine with claimable_by_me)", which is genuinely actionable. However there is no when-to-use-this-vs-alternative statement, no when-not guidance, and no note on default behavior when all filters are omitted.

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