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

The description is consistent with readOnlyHint=true — 'Browse' and 'Fetch' are read operations — and it usefully discloses that workspace prompts require is_custom=True plus workspace_id. Beyond that it adds no behavioral context such as pagination on the listing, error behavior for a missing prompt_id, or scope of the catalog. With annotations already carrying the safety profile, a 3 is appropriate.

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?

A one-line purpose statement followed by a numbered enumeration of the two modes, with each mode's applicable parameters inline. No filler sentences, and the mode structure is front-loaded so the agent can branch immediately.

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?

An output schema exists, so return-value detail is correctly omitted, and read-only safety is covered by annotations. For a five-parameter tool the description covers the branching logic and the workspace-prompt precondition well. What remains thin is the prompt_type filter vocabulary and the behavior when prompt_details is called without is_custom.

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 has to carry the parameter burden and largely does: it explains both request enum values, when prompt_id is needed, and the is_custom/workspace_id pairing for workspace prompts. The gap is prompt_type — its accepted values and effect are never explained — and is_custom's default null behavior is unstated.

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 names a specific resource and verb: browse the CallRail prompt catalog, split into a listing mode and a detail-fetch mode. An agent can map the two requests to distinct actions without opening the schema. It stops short of differentiating from the generic siblings (query_data, query_contexts), which is the only thing keeping it from a 5.

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?

Each request value is paired with the condition that selects it ('menu' to list, 'prompt_details' to fetch a body), and the per-mode optional parameters are spelled out. There is no explicit when-not-to-use guidance or pointer to a sibling tool, so it lands just under full marks.

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