compute_accuracy

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

With no annotations provided, the description carries the burden. It explains the calculation logic and parameter behavior for group_by, bucket_by, and score_name, but it does not confirm whether the operation is read-only, address edge cases, or describe interactions among date parameters (start_date, end_date, time_range).

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 extremely concise, using only three short sentences. It front-loads the core purpose and formula, and every sentence adds value. No superfluous content or redundancy.

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?

The presence of an output schema covers return-value details, but the description is incomplete on parameter semantics for half the parameters. It also lacks context on data prerequisites (e.g., how feedback scores are sourced) and default filtering behavior. For a tool of moderate complexity, it is adequate but has clear gaps.

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?

The schema has 0% description coverage, so the description must compensate. It does add meaningful semantics for group_by, bucket_by, and score_name (e.g., valid values like 'domain', 'week', 'day'), but it leaves tags, project, start_date, end_date, and time_range without explanation. This partial coverage is helpful but incomplete for a tool with 8 parameters.

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 clearly states the tool computes accuracy from feedback scores and provides the exact formula (correct / (correct + incorrect)). This specific verb+resource distinguishes it from sibling analysis tools like compute_token_percentiles or analyze_latency.

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 description implies usage by showing typical values for group_by and bucket_by (e.g., 'week', 'day' for trends), but it does not explicitly state when to use this tool versus alternatives like fetch_scores or aggregate_by_group. No exclusions or alternative tool names are mentioned.

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