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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its budget elsewhere: it discloses that average position is null when no citation has a position and that an unavailable window returns a coverage state distinct from a measured zero. Those are genuinely non-obvious semantics an agent could otherwise misread as missing data or as a real zero; only auth/project-scoping behavior is left unstated.

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 purpose and metrics, then the caveat about unavailable windows. The metric enumeration is long but each item maps to a returned value, so little is wasted; the phrasing of the second sentence is slightly convoluted but still compact.

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?

There is no output schema, and the description compensates by listing the returned fields and explaining the null-position and unavailable-window states. For a read-only, single-optional-parameter rollup tool, an agent has everything needed to call it and interpret the response.

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% and windowDays is fully documented in the schema with its enum and 30-day default, so the schema does the heavy lifting. The description adds nothing about the window parameter (not even that results are scoped by it), leaving this at the baseline for a one-parameter tool.

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 citation statistics for a project') and enumerates the exact metrics returned, so the agent knows this is a rollup tool rather than a per-page or per-domain listing. It never names the closely related siblings (devtune_get_citation_analysis, devtune_get_top_citation_pages/domains), so differentiation still requires inference from the name.

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 by 'aggregate... for a project' plus the rolling-window framing, but there is no explicit statement of when to prefer this over devtune_get_citation_analysis or the top-citation tools, and no prerequisites are given. The one clear conditional is the coverage-state note, which is behavioral rather than a selection rule.

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