search_tasks

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

No annotations are provided, so the description carries the full burden. It discloses critical behavioral traits: server-side reordering by number rather than relevance, the need to check total_matched, the incompatibility of query with root_only, the not_finished default including completed tasks, the 200-item limitation for undated, and precedence rules. This is exceptionally transparent.

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 description is long but every sentence adds value, organized with clear bullet points per parameter. It is front-loaded with purpose and scope, then dives into parameter details. The structure makes complex information digestible without wasted words.

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?

With 15 parameters, no annotations, and high complexity, the description covers the vast majority of needed context: parameter meanings, limitations, default behaviors, and response shape. The only minor gap is the 'limit' parameter, but its name and default make it self-evident, and the description explicitly mentions increasing limit when needed.

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 coverage is 0%, so the description must compensate. It provides detailed semantics for nearly every parameter: query's scope and relevance behavior, status/priority/task_type value sources, assignee/customer accepted formats, date ranges, not_finished/overdue/undated nuances, ordering options, and response fields. Even root_only's behavior is touched through its incompatibility note.

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 clearly states the verb ('searches tasks'), resource ('tasks in current repo project'), and scope (keyword/filter-based). It distinguishes itself from siblings by explicitly naming list_my_tasks and list_tasks as simpler alternatives for specific cases, which is strong differentiation.

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 provides explicit when-to-use guidance: it is for keyword or combined filters, while list_my_tasks and list_tasks are simpler for 'my tasks' and 'specific assignee tasks' respectively. It also clarifies when not to use certain parameters (e.g., query and root_only together) and how not_finished default differs from sibling tools.

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