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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds meaningful behavior beyond that: the data domain returned (resources, interactions, search parameters), the identity of the underlying endpoint (GET /metadata), and its intended role as a recovery/introspection call after a rejected search. It does not mention response size, caching, or auth requirements, but the read-only annotation makes those less critical.

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?

Three tight sentences: what it returns, when to use it, and the raw endpoint path. The most decision-relevant information (what the document contains) is front-loaded, and no sentence is redundant or padded.

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 zero-parameter, read-only introspection tool with annotations covering the safety profile and no output schema, the description supplies everything needed: content, use condition, and endpoint. An agent can decide to call this and understand what comes back without further documentation.

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?

This is a zero-parameter tool, so the baseline of 4 applies. The description correctly implies no inputs are required by describing a pure retrieval of instance metadata, and there is no parameter surface left undocumented.

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?

States a specific verb and resource ('Fetch the server's FHIR CapabilityStatement') and enumerates exactly what the document contains — resources, interactions, search parameters supported by this instance. This is clearly distinguishable from siblings like canvas_search and canvas_read, which operate on clinical data rather than server metadata.

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?

Gives an explicit positive trigger: 'Read it when a search is rejected and you want to know what the instance actually accepts.' This is actionable context an agent can match against a failure state. It stops short of a full 5 because it names no alternatives or when-not conditions, though the tool's purpose is unique enough among its siblings that routing ambiguity is low.

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