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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: results are paginated with a rollup computation per epic, and AI-traceability artifacts are filtered out of the result set — a result-shaping rule an agent could not infer from any structured field.

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 with the core capability front-loaded and the behavioral caveats (artifact filtering, status filter) after. Dense but every clause carries information; slightly telegraphic phrasing ('Filters out AI-traceability artifacts') costs a little clarity.

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 steps in to name the returned rollup fields (totalStories / doneStories / totalPoints / donePoints / progress%), which is exactly the missing context, and it flags the exclusion rule. For a read-only filtered list, nothing an agent needs to call it correctly appears absent.

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 only 25% (only projectId is described), so the description must carry more weight. It does clarify the status dimension and its three values, and 'paginated' implies page/limit usage, but it never explains page-size defaults, the 200 cap, or ordering — gaps the schema alone leaves implicit.

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 (paginated list of epics) scoped to a project, and adds what the payload contains (story-count rollup fields) plus an exclusion rule. It does not explicitly contrast with get_epic or list_stories, but the list-vs-get distinction is obvious from the name pair.

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?

Usage is implied rather than stated: 'paginated list … with optional status filter' tells the agent this is the browsing tool and that status narrows results. There is no explicit when-to-use/when-not guidance, no mention of when to prefer get_epic for a single epic, and no statement of what happens with an invalid or omitted status.

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