Observed history for past runs (descriptive)

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

With no annotations, the description fully discloses behavioral traits: 'Read-only, runs nothing', 'DESCRIPTIVE only', 'NOT a prediction', and 'local, capped, TTL-pruned store'. This exceeds the burden of transparency, especially for a read-only history tool.

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 three sentences, each serving a distinct purpose: function, transparency, and use guidance. No redundant words or fluff. It is efficiently structured and front-loaded with the core purpose.

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 description covers the data source, limitations, and usage context. However, without an output schema, it could be more complete by briefly describing the output format (e.g., a list of commands with aggregate stats). The mention of sample size and recency window is helpful but not fully specified.

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 coverage is 100%, but the description adds value by explaining that the tool provides 'observed exit/retry/duration/file-churn' and mentions sample size and recency window. These details enrich the understanding beyond the parameter descriptions in 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 clearly states 'Aggregate PAST sh_run records for a command' and lists specific metrics (exit/retry/duration/file-churn). It distinguishes itself from siblings by emphasizing 'DESCRIPTIVE only' and 'NOT a prediction', and provides a clear use case: 'Use to judge whether a command is historically slow/flaky in THIS project before running it.' This leaves no ambiguity about the tool's function.

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 gives explicit guidance on when to use the tool ('before running it') and contrasts it with predictions. However, it does not name alternative tools or specify when not to use it. Given sibling tools like sh_run and sh_plan, the guidance is clear but could be more explicit about exclusions.

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