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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable interpretative context beyond annotations: counts are 'publication-index signals, not efficacy, quality, independence, or clinical-success judgments.' This prevents misinterpretation of the tool's output and clarifies what the counts do and do not represent.

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, front-loaded with the action and resources, followed by usage guidance and a critical caveat. Every phrase earns its place with zero redundancy. This is a model of concise, high-signal description writing.

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?

The tool is a simple counting operation, and the description covers purpose, usage, and interpretation. It doesn't describe the exact output format, but the phrase 'counting... publication types' implies counts per category. Given the low complexity and strong annotations, the description is sufficiently complete, though it could optionally mention that results are grouped by type.

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%, with each parameter described and an example provided. The description doesn't add parameter-specific syntax but doesn't need to, as the schema carries the heavy lifting. Baseline 3 is appropriate; the description's mention of 'for a topic' maps to the query parameter, but adds no extra semantic depth beyond the schema.

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 ('Profile the composition') and names the exact resource ('PubMed publication types'), listing the study types counted. This clearly distinguishes it from siblings like search_pubmed and pubmed_publication_trend, and the evidence-diligence use case reinforces its unique scope.

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 explicitly states when to use it: 'Use for evidence diligence and questions like "what kinds of studies exist on this target or therapy?"'. While it doesn't name alternatives or state when not to use it, the context is clear and directive. Sibling tools like search_pubmed are implied as alternatives for different tasks.

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