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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description goes beyond that by disclosing matching behavior (8-char id prefix with optional leading '#', or a full UUID) and the shape of returned rows (agency_id/agency_name, project_id/project_name), which is real behavioral context. It does not mention pagination or limit semantics.

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 front-loaded sentences that each carry information: search scope and fields, ID matching behavior, then result columns and filtering. The trailing API reference URL is a small amount of boilerplate but is legitimately actionable.

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?

There is no output schema, and the description only partly compensates by describing returned row columns. With 6 parameters at 33% schema coverage, agency_id, client_id, and limit remain undocumented in both structured fields and prose, leaving the agent guessing on scoping and result-size control.

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 only 33%: parent_id and project_id are documented in the schema, while query, limit, agency_id, and client_id are bare. The description partially compensates by explaining what query accepts (id prefix or UUID) and reinforcing the project_id filter, but says nothing about limit, agency_id, or client_id.

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+resource with scope: 'Full-text search visible tasks by title, description, and goal' – the search fields are named and the 'visible' qualifier bounds the result set. It implicitly separates itself from list_my_tasks / list_client_tasks / get_task by being full-text rather than a listing or single fetch, but it never names a sibling to route the agent explicitly.

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?

Implies usage via 'filter by project_id to see one project's work,' which tells the agent how to narrow scope. However there is no when-to-use-this-instead-of guidance versus the many sibling listers (list_my_tasks, list_client_tasks, get_task), and no stated preconditions or exclusions.

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