read_output

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

With no annotations, the description carries the disclosure burden and it explains the non-obvious behavior: it returns aggregate stats (count, first, last, min/max with locations, negative count) rather than raw output. However, it does not comment on error conditions, exact return formatting, or how optional filters interact with the summary.

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?

One tightly worded sentence front-loads the action and target, then lists the concrete statistics in a compact enumeration. There is no filler or repeated schema content.

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 read-only summarizer with full schema parameter documentation, the description covers what the output contains, which compensates for the absence of an output schema. Minor gaps remain (error behavior, exact result shape) but they are not essential for selecting and invoking the tool.

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 explains file, column, where, and label_by. The description adds a little semantic color by explaining that min/max locations are reported, which maps to label_by, but it does not meaningfully enrich the other 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 names a specific verb ('Summarise'), a specific resource ('a column of a run's output file'), and enumerates the exact computed statistics. This clearly distinguishes read_output from the code-analysis sibling tools, none of which perform output-file summarization.

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?

No explicit when-to-use/when-not-to-use guidance is provided, and no alternative tools are named. The only usage context must be inferred from the purpose statement itself, which carries no exclusions or choice criteria.

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