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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the agent knows this is a closed-world, side-effect-free computation. The description adds that results are computed rather than looked up (RETURNS line naming the three derived scores), but says nothing about handling of percentages that do not sum to 100, validation failures, or which score applies to which stain_type. With annotations carrying the safety profile, this is adequate but 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?

The definition is compact and pipe-delimited with front-loaded USE WHEN and RETURNS segments, which makes it easy to scan. It is also somewhat template-like: the header line repeats the title verbatim and the bilingual aliases pad the text without adding selection signal beyond the first few terms.

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?

For a five-parameter, single-purpose calculator with full schema coverage and a read-only annotation set, the description covers what it computes and what it returns. The remaining gap is that the accepted stain_type values and the arithmetic constraint on the intensity percentages are unstated in both the description and the schema, which matters for a scoring tool.

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 100% and the schema labels the parameters (stain_type, intensity_0_pct through intensity_3_pct) with units as percentages. The description adds real value by tying those intensity buckets to the named scoring systems (H-score, Allred, positive rate), so the agent understands why the 0/1+/2+/3+ split is required. It does not state whether percentages must sum to 100 or what stain_type values are accepted.

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 names a specific analytical operation (immunohistochemistry scoring) and enumerates the concrete outputs it produces (H-score, Allred, positive rate), which distinguishes it from nearby siblings like gleason_grade_group or mif_phenotype. It stops short of explicitly contrasting itself with those siblings, but the domain vocabulary is specific enough for an agent to pick it correctly.

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?

'USE WHEN: immunohistochemistry scoring from staining intensity percentages' gives an implied trigger condition tied to input data shape, which is more than a bare purpose statement. However, there is no when-not guidance and no mention of alternatives, so an agent facing borderline cases (e.g. a categorical stain readout or an image-based nuclei count) must infer the boundary itself.

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