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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context beyond these: it clarifies that publication linkage reflects acknowledged grant support (not impact/causality) and that the sample is bounded. This helps prevent misinterpretation of results.

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 description is two sentences: the first states the core action, the second adds a crucial caveat about what the linkage is not. No filler or redundant repetition; it is front-loaded and every sentence 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?

There is no output schema, so the description must clarify return values. It mentions 'return a bounded PMID sample' and implies a count, but does not specify the exact response structure, field names, or whether pagination exists. For a simple tool this is adequate but incomplete for a detailed invocation.

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 only 50%: 'limit' is well-described in the schema, but 'core_project_num' has no description. The tool description only repeats 'core project number' and 'bounded PMID sample', adding little meaning beyond parameter names. The schema example shows a format (UG1HD078437), but the description does not compensate for the undocumented required parameter.

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 uses a specific verb 'Count' with a clear resource ('publications linked by NIH RePORTER to a core project number') and specifies the output ('bounded PMID sample'). It also explicitly distinguishes itself from citation-impact measures, which differentiates it from sibling tools like search_publications or validate_claim.

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 description provides an explicit when-not by stating it is 'not a citation-impact, product-readiness, or causal-attribution measure,' which tells the agent not to use this tool for those purposes. However, it does not name alternative tools or provide explicit 'use when' conditions, so it falls short of a 5.

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