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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious context beyond them: answers are evidence-citing, and each call consumes the project's Ask Relia allowance, which flags a cost/quota dimension the agent should weigh. It does not disclose latency, determinism, or what happens on exhausted allowance, which keeps it short of a 5.

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?

Three short sentences, front-loaded with the capability and followed by three compact parenthetical examples that carry most of their informational weight. Minor space spent on illustrative quotes, but no sentence is filler.

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 must characterize the return value, and it goes only as far as 'answers cite their evidence'. For an open-ended NL answer tool an agent would benefit from knowing the shape of a response (prose vs. structured), typical latency, and behavior when allowance runs out or the project is ambiguous.

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 50%: the `project` parameter is documented in the schema as only needed for multi-project tokens, while `question` has no schema description at all. The description partially compensates by demonstrating the kind of natural-language question expected, but adds no guidance on scope, length, or phrasing limits beyond the examples.

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?

Names a specific verb (ask a question) and a specific resource (the product's live data) and grounds it with three concrete example questions, so an agent can immediately tell this is a natural-language query interface rather than a metrics endpoint. It does not name the sibling tools (relia_uptime, relia_logs, relia_dashboard) that answer narrower versions of the same questions, so the differentiation from siblings is implied rather than stated.

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 examples imply when this is useful (diagnostic questions spanning uptime, API latency, and error causes), and 'Uses the project's Ask Relia allowance' hints that it is a metered resource worth conserving. However there is no explicit guidance on when to prefer a targeted sibling like relia_uptime or relia_logs over this open-ended tool, nor any exclusion condition.

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