Run cheap reading job

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

Annotations declare a non-read-only, open-world, non-idempotent, non-destructive job, and the description adds the traits that matter beyond them: each call is a paid job charged against daily_budget_usd, quotes/line refs are validated against the source, and output is capped by max_tokens. It does not however explain the async lifecycle or export/overwrite side effects in prose.

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?

Three sentences, no filler, with the core action first, the cheaper alternative second, and the cost/result-routing constraints last. Every clause carries actionable information for the caller.

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 12-parameter, multi-mode, model-invoking tool with no output schema, the description covers purpose, cost, verification behavior, the free alternative, and where results are retrieved. It leaves the async polling path and export_to behavior to the schema, which is a minor gap rather than a blocking one.

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 modes, files semantics (globs, URLs, #L100-L400 single-file range), time window and schema dialect are all documented in the schema itself. The description adds only the cost cue for grep mode and the 30 KB threshold, so it meets but does not exceed the baseline.

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?

States a concrete verb+resource: hand a reading-by-meaning job over large text (logs, archives, long documents, web pages) to a cheap model. It scopes the tool ('large text', implicitly >~30 KB) and distinguishes itself from the free grep path and from the sibling eyes_result that returns the output.

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?

Explicitly gives the when-not case and the alternatives: 'For exact values, structure or files under ~30 KB use mode grep ($0) or your own file tools.' It also tells the agent where the full result lands (eyes_result), which resolves the run-then-fetch workflow.

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