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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by mentioning the educational nature ('never medical advice'), evidence grounding ('PubMed-grounded'), safety rails in protocol compilation, and per-endpoint pricing. It also indicates coverage is global. However, it does not specify authentication requirements, rate limits, or response format details, so it is not fully transparent.

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 longer than typical, but it is well-structured with a clear first paragraph summarizing the tool and a bulleted list of endpoints. Each bullet is short and informative. The structure aids scannability, though the opening paragraph is somewhat marketing-heavy. It earns a 4 for being appropriately organized and not overly verbose.

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?

Given the complexity of 10 endpoints and 19 parameters, the description provides a good high-level map but does not explain return value shapes or usage examples. With no output schema, the description should give more detail about what each endpoint returns; the short labels (e.g., 'Herb profile') are minimal. The description is adequate but leaves gaps for agents needing to know response structure.

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?

The schema covers 100% of parameters with descriptions, so the baseline is 3. The tool description itself does not add parameter-level meaning beyond the schema. While many schema descriptions are tautological (e.g., 'herb: herb'), the description's endpoint list does help map the 'action' parameter to use cases, providing some added context. Overall, the description does not compensate for the weak schema descriptions.

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 clearly states that HerbaPulse is a centralized natural-remedies layer with 10 endpoints, and then enumerates each endpoint (herb, remedy, ingredient, interaction, skin, tradition, practitioner, cannabis, protocol, apothecary) with a short label. This gives a precise verb+resource scope for each action and distinguishes the tool from other pulse tools, which focus on different domains.

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 clear context for when to use each action by listing the endpoints and their purposes (e.g., 'remedy: Cross-cultural remedy lookup', 'interaction: Herb-drug interaction checker'). It also includes an important exclusion: 'Educational, never medical advice.' However, it does not explicitly compare this tool to sibling tools like nutripulse or cite alternatives, so it misses the top score for explicit when-not/alternatives.

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