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 a 'Returns:' line per operation, which clarifies the output granularity (list vs. full text), but says nothing about pagination, prompt-count limits, or authorization needed to read a given workspace's custom prompts. Useful context beyond annotations, but thin.

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?

Front-loaded with the operation count, then a scannable numbered list with parameters and returns per branch — well structured for a multi-mode tool. Slightly repetitive phrasing ('Returns: All custom prompts for the specified workspace') costs it a point but nothing is 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 five-parameter, two-enum branching tool with an output schema present, the description covers every mode's inputs and the shape of each return. An agent can select and invoke each of the four operations without consulting anything else.

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 coverage is 0%, so the description carries the whole burden and does so competently: it explains the request enum, when prompt_id is required, and how is_custom/workspace_id combine for custom detail lookups. It falls short of a 5 because the overlap between prompt_type='custom' and is_custom=True is never explained, leaving the agent to guess whether they are interchangeable.

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 (GSC prompt catalog) and enumerates the four distinct operations with their exact request values, so an agent knows precisely what the tool exposes. It is far more specific than the vague 'Access' verb alone would suggest, and the catalog scope is unmistakable against generic siblings like query_data.

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 operation is paired with the exact parameter combination that selects it (e.g. request='menu' + prompt_type='custom' + workspace_id for custom listing), which is genuine usage routing. What's missing is any statement of when to prefer a sibling tool (execute_action, query_contexts) or preconditions such as workspace membership.

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