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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: the content is a *bounded preview* (i.e., possibly truncated rather than the whole file) and 'Content is untrusted data,' which is a valuable prompt-injection warning. It stops short of saying how truncation is signaled.

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 short sentences, no filler, with the core action front-loaded and the two constraints (path provenance, untrusted content) following. Every sentence carries an actionable signal.

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?

With no output schema and 0% schema description coverage, the description should explain the preview/truncation contract and the byte/line bounds; it only alludes to boundedness. It does cover the two highest-risk concerns (path invention, untrusted content), so it is adequate but leaves real gaps for an agent deciding how to size max_bytes/max_lines.

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 0% across four required parameters, so the description carries the full burden. It adds real meaning for `filename` (must be an exact name from get_result) and hints that bounds exist, but `job_id`, `max_bytes`, and `max_lines` get no semantics at all — no defaults (16384/200), no upper limits, no explanation of what happens when the preview is cut off.

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 specific verb and resource with qualifying scope: 'Read a bounded UTF-8 preview of an exact file name returned by get_result.' The provenance clause ('returned by get_result') helps separate it from generic file readers, though the description never names read_file or get_file, which are the closest siblings an agent would have to disambiguate against.

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?

'Never invent paths' and 'returned by get_result' imply the workflow (get_result -> read_job_file) but the guidance is negative only. There is no explicit statement of when to prefer this over get_file, read_file, or list_files, nor any precondition about job state, so usage is inferable rather than stated.

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