analyze

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

The description adds behavioral context beyond the readOnlyHint annotation: it writes nothing (consistent), works on specific data sources, requires debug.enabled for one lens, and is advisory. This is valuable supplementary information.

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 detailed but reasonably concise, with the main action front-loaded. The mention of a slash command is slightly extraneous, but overall it is well-structured and informative without being verbose.

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 no output schema, the description adequately explains what the tool returns (advisory tuning suggestions with specific examples) and clarifies the output's advisory nature. It covers the two lenses and their lack of join, plus a requirement. This is complete enough for agent understanding.

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 the schema already provides clear parameter descriptions (sessions count, limitBytes). The tool description adds general context about the data sources but does not add new semantics beyond the schema.

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 explicitly states what the tool does: analyze recent runs from the debug log and session store, then return advisory tuning suggestions. It specifies two lenses (timing and agreement), notes they are not joined, and mentions it is read-only. This clearly distinguishes it from siblings like 'architect' or 'debugger'.

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 provides usage context: it is for obtaining advisory tuning suggestions. It notes the requirement 'debug.enabled' for the timing lens and that it writes nothing. However, it does not explicitly state when not to use it or compare to alternatives.

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