search_tasks

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the AND-combination rule, that unset filters are ignored, and that done defaults to open-only. It says nothing about result ordering, the effect of limit/pagination, or whether unset boolean filters like frogged/backburner behave as 'ignore' vs 'false' – a real ambiguity for nullable booleans.

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 short sentences plus a compact set of quoted intents; the ANDing rule and ignore-unset rule are front-loaded. No filler, though the quoted examples are slightly redundant with one another.

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 structure needn't be described, and the AND/unset semantics cover the query model adequately. For an 18-parameter tool with several undocumented filters and no pagination or ordering guidance, the definition is minimum-viable rather than complete.

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?

18 parameters at 67% schema coverage sits between the 50% and 80% baselines, so the schema does most of the work. The description adds only the global AND/unset-filters rule, leaving undocumented params (frogged, backburner, has_due_date, has_estimate, limit, include_subprojects) unexplained in either place.

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?

Names a specific verb (Find) and resource (tasks) and states the core semantics (any combination of filters, all ANDed, unset ignored). It is clearly distinguishable from the sibling writers (create_task, update_task) and even implies it subsumes the narrower listers, though it never names list_today/list_due 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?

The quoted example intents ('what can I do in 5 minutes', 'everything tagged X', 'scheduled this week in project Y') give concrete selection context and map naturally onto max_minutes, labels, scheduled_from/scheduled_to, and parent. However it gives no exclusions or explicit pointers to list_today / list_due / list_inbox when those narrower tools suffice.

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