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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world). The description adds substantive behavior beyond them: fuzzy/semantic matching tolerant of word forms and typos, rejection of numeric queries, and the pagination protocol (cursor of last item with the same query and filters). It stops short of describing result ordering or what the result objects contain, but that gap is minor given no output schema requirement is stated.

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 tight sentences front-load the core purpose and then append the pagination mechanic. The semicolon-joined clauses are dense but each carries real information; nothing is padding. Slightly cryptic phrasing ('the next page takes the last item's cursor') keeps it from a 5.

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?

For a read-only search with a fully documented schema and no output schema, the description covers purpose, the key semantic-matching behavior, the numeric-query rejection, pagination, and the allowClosed flag. It leaves result ordering and sourceTaskID semantics to the schema, but nothing essential to correct invocation is missing.

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 100%, so all six parameters are documented in the schema. The description adds meaning only for a few: it clarifies that allowClosed includes closed tasks, that the cursor comes from the last item of the same query/filters, and that query is not a task number. For limit, productID, and sourceTaskID it adds nothing beyond the schema, so the baseline 3 is appropriate.

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 (searches) and resource (a product's tasks and bugs) and explicitly bounds the scope: semantic matching over titles, gists, specs and results, tolerant to word forms and typos. It also names what it is NOT for (task numbers like #12345 are rejected), which differentiates it from number-based lookups among the task_* siblings.

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?

It clearly states the condition for use (when the number is unknown) and gives an explicit exclusion (task numbers rejected as queries), plus explains how to paginate. It does not name a specific alternative sibling to use when the number IS known, so it falls one step short of fully routing the agent.

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