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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows the source trace is not rewritten and no network call occurs; 'computed here' reinforces the openWorldHint=false claim. Beyond that the description adds little behavioral context — it does not say whether trimming is reflected only in the returned record, how bounds behave when no base passes the threshold, or what happens with an empty trim result.

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?

A single sentence with the action front-loaded and the mode distinction following immediately; nothing is padded. The clause 'that answer different questions' is slightly rhetorical where a concrete criterion would have been more useful, but the sentence still earns its length.

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 six parameters (including a deeply nested _subject), full schema coverage, and an output schema, the structured data does most of the work, so the description only needs to supply the method-selection rationale and the non-mutation guarantee. It gestures at the former without resolving it, which is the main remaining gap for a trimming tool where choosing the wrong method silently changes results.

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%, including the method enum's auto/mott/window semantics, so the baseline of 3 applies. The description's framing of the two methods as answering 'different questions' adds a conceptual gloss but no concrete meaning beyond what the parameter descriptions already provide.

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 ('Trim a Sanger read's low-quality ends') and immediately names the two operational modes (instrument Mott record vs. computed sliding mean-Phred window). It is distinguishable from adjacent quality tools like recompute_trace_quality or call_bases_from_trace, but it never explicitly contrasts itself with the sibling trim_reads, leaving that boundary to inference.

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 phrase 'two methods that answer different questions' signals that method choice matters, but the description never says which question each answers or when an agent should override the 'auto' default. The enum documentation in the schema carries the actual selection logic, so the description only implies usage rather than stating it.

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