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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral value beyond them: the dual response shape (covered true/false), the empty-shelf fallback when no topic matches, and the obligation to carry citations when using numbers. Auth, rate limits and latency are not mentioned.

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 tight paragraphs, front-loaded with purpose, then the return contract and the citation obligation. The enumeration of shelf fields is justified because no output schema exists, and no sentence is filler.

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 no output schema, the description carries the return-value burden and does so by naming both response shapes and their payload fields. What remains thin is the operational side: behavior on ambiguous or unsupported queries beyond "covered: false," and the topical scope of the library.

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?

There is a single required parameter with 100% schema description coverage, so the schema already defines it. The description reinforces the domain ("clinical-evidence question") but adds no guidance on question phrasing, granularity or scope, which is the baseline 3 case.

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 and resource ("Ask SourceMed a clinical-evidence question") and explains that it hits the library's Ask endpoint returning source-verified cards, which is clearly distinct from the get/list/search shelf siblings. It stops short of explicitly naming those siblings as alternatives, so it is clear but not fully differentiated.

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 by the framing: ask a natural-language clinical-evidence question and get back verified cards. There is no explicit when-to-use statement, no exclusions, and no pointer to the structured shelf tools for browsing instead. An agent must infer the routing decision.

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