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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds context about authentication methods and the hosted/local endpoint distinction, which is valuable beyond the structured annotations. No contradiction exists.

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 two sentences, front-loaded with the main purpose followed by essential usage details. Every word earns its place, with no redundancy.

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 absence of an output schema and the tool's simplicity, the description provides enough operational context: how to specify the target intake and the endpoint mode. It doesn't describe the return structure, but that's not required without an output schema and the read-only annotations cover side effects.

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 75% (three of four parameters have descriptions). The description clarifies that session_id must be used with access_token, and explains api_base_url's purpose for local stdio use, adding meaning not fully captured in the schema. However, session_id itself remains 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?

The description uses a specific verb ('Get') and resource ('current applicant intake state'), making the tool's core function clear. It doesn't explicitly differentiate from siblings like 'open_intake' or 'get_case', but the resource and state focus distinguish it sufficiently.

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 explains the two ways to call the tool (url or session_id with access_token) and notes the hosted MCP endpoint distinction from local stdio via api_base_url. However, it doesn't state when to prefer this tool over alternatives or mention any exclusion criteria.

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