search_issues

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description adds useful non-obvious behavior — the priority-then-due-date ordering — but omits the truncation behavior implied by the limit parameter (default 20), which is the main behavioral risk for a search tool. It also doesn't say whether results are scoped to a single project only.

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 sentences, front-loaded with the verb, resource, and ordering, with no filler. The filter enumeration is compact and scannable. Minor deduction for a stray trailing newline and for listing filters without grouping by which are mutually exclusive or combinable.

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 needn't be described. However, for a six-parameter search tool the description never explains the limit/pagination contract or the role of the required project_id, leaving an agent unable to reason about result truncation. Adequate but with a real gap for a listing tool.

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 0%, so the description carries the full burden and does meaningful work: it enumerates the status values (open, in_progress, closed), gives the priority range (low..critical), and supplies example discipline values ("MEP", "Structural") that the bare string schema does not convey. It leaves limit and the required project_id entirely unexplained, which keeps it from a 5.

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 and resource ("Find issues on a project") plus the result ordering ("sorted by priority then due date"), which is genuinely differentiating information. It implicitly separates itself from the single-record sibling get_issue, but never names that sibling or search_documents explicitly, so it stops short of full sibling 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 filter list implies the intended use case (narrowing a project's issue set), but there is no explicit when-to-use guidance, no mention of when to prefer get_issue for a known ID, and no statement about what an unfiltered call returns. Usage must be inferred from the parameter enumeration.

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