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

Annotations already establish readOnly/non-destructive, so the bar is lower, and the description adds genuinely non-obvious behavior: the scan is 3'-anchored, every reported site matches the 3' seed exactly, and 'no sites' means no seed match rather than a low score. It also notes the effective cutoffs are echoed back in `thresholds`. It does not cover failure modes or input-validation behavior, keeping it short of a 5.

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?

Two sentences, purpose front-loaded, with the essential 3'-anchored caveat second; no filler or restatement of the tool name. The first sentence is dense with symbols and grading vocabulary, which slightly slows parsing but every clause earns its place.

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 an output schema present, return values need not be spelled out, and the description still explains scope, verdict grading, and empty-result semantics. The one gap is that it says 'the open plasmid' while the schema also accepts arbitrary `_subject`/`_files` records, leaving the target-selection rule slightly ambiguous.

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 3 is the baseline and the schema already explains each threshold symbol and the 99.999 exact-cut rationale. The description still adds value by framing thresholds as a movable bar tied to intent ('move it to say what you are asking', pool-screening vs clone-checking) and reiterating that the bar used is returned.

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?

The description gives a specific verb+resource: it maps where a primer anneals on the open plasmid, reporting 3'-anchored sites with identity % and a graded verdict. The 'on the open plasmid' scope and the 3'-anchored seed semantics separate it from sibling tools like check_primer_specificity and find_primer_snps, so an agent can route correctly without opening schemas.

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?

Usage is implied rather than stated: the tool is for locating primer binding sites on a plasmid, and the threshold-taste note ('screening a pool tolerates a lower strong than checking a clone') is real but parameter-level guidance. No explicit when-to-use-vs-alternative or exclusion (e.g., when to prefer check_primer_specificity over this) is given.

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