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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real behavioral context beyond them: results are server-computed over the elected delivery feed (not a sampled approximation), and the deliveryFeed parameter defaults to PAT or project settings. It stops short of disclosing cost, latency, or pagination, but that is minor.

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?

A single sentence front-loads the verb and resource before the metric list, and every clause carries information (the 'not a sample' caveat is the strongest value-add). It is dense but not padded; a slight readability cost from the long comma-separated metric enumeration keeps it off 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?

With no output schema, the description responsibly enumerates the returned metrics so the agent knows what it receives, and all parameters are schema-documented. What remains unstated is the response's relationship to the days window (e.g. whether MTTR and health score are scoped to that window) and whether cost scales with it — a modest gap for an analytics 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 coverage is 100%, so all three parameters (days, projectId, deliveryFeed) are already documented with defaults, bounds, and enum values. The description reinforces that the feed election affects which bugs are aggregated but adds no syntax or windowing detail beyond the schema, so baseline 3 applies.

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 ('Get aggregate statistics for a project') and enumerates exactly what is aggregated: status/severity counts, timeline, top unresolved bugs, MTTR, health score, period comparison. This is clearly distinguishable from siblings like get_bug or list_bugs, which return individual records rather than aggregates.

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: 'aggregate statistics for a project' signals this is the aggregation counterpart to list_bugs/get_bug, and 'server-computed... not a sample' hints it should be preferred over client-side counting. But there is no explicit when-to-use/when-not or named alternative, leaving the routing inference to the agent.

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