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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context — computation happens for all spacers in a single pass over one sequence — but says nothing about cost, runtime, or the sensitivity trade-offs of the mismatch-class sweep. Adequate, not rich.

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 tight sentence with the action and scope front-loaded, followed by the triage rationale. The 'question that comes BEFORE...' clause is slightly rhetorical but earns its place by conveying usage order; nothing is redundant.

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?

There are 9 parameters including nested record references and an output schema, so returns need no explanation. However, the description never signals that the nuclease choice determines PAM/geometry (a consequential decision among ten options) or that bulge settings exist, leaving the agent to discover the most impactful knobs purely from the schema.

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 every parameter (nuclease with per-enzyme PAMs, dna_bulge, rna_bulge, max_mismatches, circular, subject, _subject, _files) is already documented in-schema. The description only echoes 'by mismatch class' and 'across one sequence,' adding no format or default guidance beyond that 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?

Specific verb plus resource: 'Count every guide's off-target sites by mismatch class across one sequence, in one pass.' It names the unit of work (all spacers at once, one sequence) and implicitly distinguishes itself from the per-guide sibling search_off_targets by contrasting with 'opening any single guide's site table.' An agent can tell this is the batch triage counterpart, not the deep per-guide lookup.

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?

Clear situational framing: this is the question that comes 'BEFORE' drilling into a single guide's site table, i.e. use it to rank spacers for further scrutiny. It does not explicitly name search_off_targets or screen_guides as the follow-up alternatives, so the routing is inferable but not stated.

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