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

Annotations only cover read-only/idempotent, and the description adds substantial behavioral detail beyond that: bot and dependabot PRs are excluded from the outcome comparison, the result explicitly states when samples are too small to compare, and the attribution block separates first-party reports from inferred diffs and grades the inference. This pre-warns the agent about data-quality caveats and error margins before it acts on numbers.

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?

The description is front-loaded with the core question and keeps every sentence substantive, with no filler. It runs long (~180 words) and the attribution paragraph could be tightened, but each statement carries operational meaning.

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?

Given an output schema exists and annotations cover the safety profile, the description supplies everything else an agent needs: what the metric means, caveats about sample size and detection coverage, exclusion rules, and how to interpret attribution confidence. Nothing material to correct invocation is missing.

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 both the period enum and the repository slug (including the important note that it resolves the team but does not filter metrics) are already documented in the schema. The description adds no parameter syntax, defaults, or format guidance beyond that. Baseline 3 is appropriate when the schema does all the work.

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?

The description names a precise question the tool answers ('how much of this team's shipped work is AI-assisted') and enumerates the specific outputs: adoption rate, contribution intensity, AI-assisted PR rate, detected tools, detection confidence, and an outcome split on lead time and size. It also gestures at differentiation from siblings by naming report-ai-usage-tool as the source of first-party attribution data. An agent can distinguish this from get-mcp-adoption-tool and get-dora-metrics-tool from the description alone.

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?

It gives explicit use cases ('is AI actually in our SDLC yet' and 'is it paying off') and frames the outcome split as the KPI vs adoption as a pilot metric, which tells the agent when this call is warranted. It also warns that results flag small samples and uncovered detection periods. However, it never states when NOT to use this tool or routes the agent to a specific alternative sibling for partial needs.

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