get_scan_prompt

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

With no annotations, the description carries the burden. It states 'Read-only' upfront, which is a key behavioral trait, and explains the filtering behavior (only NOT_IMPLEMENTED controls). It does not elaborate on return format or pagination, but the output schema covers that. The description adds meaningful context beyond what the schema provides.

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 three concise sentences with no fluff. It front-loads the purpose, includes the read-only note, and gives downstream tool guidance. Every sentence adds value and is structured for easy scanning.

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 read-only prompt-retrieval tool with an output schema, the description is largely complete. It explains the scoping behavior and follow-up actions. The only minor gap is the undocumented server_version parameter, but this is a schema issue rather than a description shortfall.

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 67%, with model_id and control_id already described. The description reinforces the control_id default behavior (empty returns all not-yet-implemented controls) but adds little beyond the schema. server_version has no description in either, so the description does not compensate for that gap.

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 opens with a specific verb and resource: 'Get guidance prompts for scanning a codebase to discover control gaps.' It clearly states the tool's function and differentiates it by specifying that only NOT_IMPLEMENTED controls are included, which separates it from sibling tools like get_controls or get_functional_scan_prompt.

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 provides explicit usage context: 'Use this to drive a gap-discovery pass, then record what is missing with submit_findings and what is present with submit_assertions.' It tells the agent when to use the tool and what to do afterward, while also clarifying that implemented controls need no scan, so the tool is specifically for not-yet-implemented ones.

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