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

With no annotations, the description takes on heavy responsibility. It discloses the two-step behavior, what returns in discovery (names and inputSchemas), that execution returns real data directly, and that the tool name must match exactly. It doesn't mention side effects or permissions, but the core behavioral workflow is clearly documented.

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 well organized with clear STEP 1 and STEP 2 markers, using a compact list format. Every sentence adds value, and the critical directive about not calling other tools is prominent. No redundancy or filler is present.

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 tool's complexity (5 params, nested objects, two-phase usage) and lack of an output schema, the description covers the core flow and return values well enough for an agent to invoke it correctly. It does not detail error cases or edge scenarios, but for a tool finder gateway, the described two-step protocol is sufficient for expected use.

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?

Although schema coverage is 100%, the description adds meaningful phase-specific semantics for parameters like 'tool_name' ('exact tool name from previous discover response') and 'tool_args' ('arguments matching the tool's inputSchema exactly'). It clarifies the role of 'query' as user intent and the optional 'team' filter, going beyond mere schema repetition.

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 identifies the tool as a two-step finder and executor for all enterprise APIs, with a specific verb ('discover'/'execute') and resource. It explicitly distinguishes its role by stating that no other tool should be called directly, making it unique even without siblings.

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?

It provides explicit step-by-step usage instructions: STEP 1 for discovery with only 'query', and STEP 2 for execution with 'query' + 'tool_name' + 'tool_args'. It also gives a strong directive ('You NEVER call any other tool directly') that clarifies when to use this tool versus any alternative.

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