Describe a tool

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

Discloses non-obvious behavior beyond annotations: unknown server/tool names return the valid ones rather than erroring, and the return payload is 'each argument and its type'. 'Read-only' merely restates readOnlyHint=true (consistent, not contradictory) and could be dropped. The 'detail' mode's behavioral difference is left undisclosed.

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?

Four short clauses, each carrying a distinct fact (what it returns, when to call it, naming semantics, error fallback), with the action front-loaded. No 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?

Covers the essentials for a 3-param, no-output-schema tool: return shape is summarized in prose, mutation/error behavior is stated, and usage ordering is given. The unexplained 'detail' parameter is the one remaining gap an agent would hit in practice.

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 0%, so the description must carry the load: it does explain that server/tool are catalogue names and that an unknown value returns valid alternatives, which is valuable. However, the 'detail' enum (compact vs full) is completely unexplained in both schema and description, leaving no clue about what changes in the response.

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 ('Get the arguments of ONE backend tool') with explicit scope ('ONE'), which cleanly distinguishes it from siblings list_capabilities and call_tool. An agent can tell immediately this is a schema-introspection call, not an invocation.

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?

'before call_tool' gives a concrete ordering rule that tells the agent when to use it relative to the primary sibling. It does not address when to use list_capabilities/search_capabilities instead for discovery, which is the only missing routing guidance.

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