count_issues

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

The readOnlyHint=true annotation already establishes this as a safe, non-mutating read. The description adds little beyond that: it doesn't say whether counts are exact or approximate, whether the query language can be passed alongside filter, or how results are bounded. Essentially no behavioral context beyond the annotation.

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?

One short, front-loaded sentence with zero padding. Nothing to trim and the key noun ('number of issues') appears immediately.

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 no output schema, the description does at least state the return is a count, which covers the essentials for a trivial aggregation tool. What's missing is how the three optional, non-required parameters interact when several are supplied.

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 the schema already documents query ('Tracker query language string'), queue ('Queue key'), and filter. The description echoes 'filter or query' and omits queue and any precedence rules, 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+resource pair ('Get the number of issues') and the scoping dimension ('matching a filter or query'). It is clearly distinguishable from find_issues by being a count rather than a listing, though it never names that sibling 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?

No guidance on when to use this instead of find_issues or search_entities, and no statement about what happens if query, queue, and filter are combined. The agent must infer that this is the cheap 'how many?' alternative to a full search.

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