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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered structurally. The description adds real value beyond that by flagging the analysis as 'heuristic' and bounding its claims (no genome-wide off-target search), which sets expectations about false negatives. It does not disclose what the result looks like, whether findings are pass/fail or scored, or how the input format is detected, so the behavioral picture remains partial.

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 dense sentence plus a one-clause caveat, front-loaded with the operative phrase 'Heuristic QC'. The parenthetical groupings map cleanly onto the three input families and earn their space. Slightly over-packed — three domains and six checks in a single sentence demands a second read.

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?

Given two parameters, no output schema, and a readOnly annotation, the description covers what is checked for each input type and one important scope limit. It is still silent on output shape, severity thresholds, and input auto-detection, all of which matter for a tool that accepts four different formats through one string field. Adequate but with clear gaps.

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 50%: 'input' is documented in the schema, but 'nuclease' is a bare enum. The description partially compensates by naming SpCas9/SaCas9/Cas12a in the PAM-check parenthetical, which implies the parameter selects which PAM rule set is applied. It still does not state the default when 'nuclease' is omitted, nor how the tool decides which of the four input formats it received — the most consequential ambiguity for a single free-text 'input' field.

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?

Uses a specific verb-plus-resource framing ('Heuristic QC for CRISPR guide RNAs... FASTA sequences... HL7 v2 headers or sample manifests') and enumerates the concrete checks (GC%, PAM, poly-T, homopolymers, seed checks). The scope is unambiguous, though the multi-modal grab-bag of three unrelated input families makes the tool's single purpose slightly diffuse. No sibling differentiation is offered, but the siblings listed (battery_passport_check, pqc_tls_scan, urdf_validate, etc.) share no domain, so disambiguation is not needed here.

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?

There is one explicit when-not ('Not a substitute for genome-wide off-target search'), which is genuinely useful for routing. However, there is no positive when-to-use guidance, no statement of what the tool assumes about input, and no explanation of how to choose between the guide/FASTA/HL7 modes. Usage is implied by the input listing rather than stated.

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