collect_performance_evidence

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows the tool is safe and read-only. The description adds no behavioral details beyond listing evidence types; it does not disclose potential execution of the query when execute_query=true or require special policies. With annotations covering the safety profile, the description provides minimal additional value, so a score of 3 is appropriate.

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 a single, front-loaded sentence: 'Collect Azure SQL resource, Query Store, wait, blocking, statistics, parameter-sensitivity, and regression evidence for a performance case.' It is concise, contains no fluff, and efficiently conveys a large amount of scope information. Every word earns its place, making it highly scannable.

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 tool has 9 parameters, an output schema, and a clear relationship to a performance-case workflow. The description gives the high-level purpose but omits contextual details such as the connection to start_performance_case, the general output structure, or how the evidence categories relate. The output schema and annotations reduce the burden, but for a tool of this complexity, the description leaves notable gaps, earning a 3.

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 56%, meaning several parameters (decision_id, database_name, window_minutes, idempotency_key) have no description in either the schema or the main description. The description itself does not explain any parameter semantics and fails to compensate for the uncovered parameters. Even for covered parameters, the description adds no contextual meaning beyond what the schema already provides.

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 uses a specific verb 'Collect' and names a specific resource ('evidence') with an enumerated list of evidence categories: Azure SQL resource, Query Store, wait, blocking, statistics, parameter-sensitivity, and regression. It explicitly ties the action to 'for a performance case', which distinguishes it from sibling tools that target individual diagnostics (e.g., get_wait_stats, detect_parameter_sniffing). This makes the tool's purpose and scope immediately clear.

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 clearly indicates the tool is for gathering comprehensive evidence in the context of a performance case, implying it is the umbrella collection tool. However, it does not explicitly state when to prefer this over the more specialized sibling tools, nor does it mention exclusions. The context is clear but lacks explicit alternative guidance, so it earns a 4 rather than a 5.

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