how

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

Beyond the readOnlyHint annotation, the description reveals the data source (commands user's agents ran), ordering (by number of separate sessions), and that records are excluded from ordinary search. It does not detail error conditions or response format, but the added source and ranking context is valuable.

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 well-structured and front-loaded: it defines the output in the first sentence, gives a direct use case in the second, then details query parameters and uniqueness. Every sentence contributes, with no unnecessary words.

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?

For a retrieval tool with no output schema, the description is comprehensive: it explains what, how, when, and why, and notes the scope parameter. It doesn't describe the return shape, but the essential context for invoking correctly is present.

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 input schema fully covers all three parameters with descriptions, so the baseline is 3. The description adds example queries and reiterates the 'every word must appear' constraint, but it doesn't introduce significant semantic detail 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 states exactly what the tool does: returns the real command with real flags used by this user on this machine, sourced from agent-run commands and ordered by session frequency. It clearly distinguishes itself from ordinary search by noting command records are kept out of it, separating it from sibling tools.

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 explicitly tells the agent when to use it: 'Call before inventing a build, test, deploy or debug invocation.' It also warns that guessed commands are plausible and fail, providing clear context for preferring this tool over alternatives.

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