CAP project context (codebase-aware)

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly states the tool compiles the project to CSN (implying it reads/parses the codebase) and returns a 'digest', but does not disclose whether it modifies anything, performance for large projects, or failure behavior for invalid CAP projects. The read-only nature is implied by 'returns a digest' but not stated explicitly.

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?

Two sentences, zero waste. The first sentence lists exactly what the digest contains, the second gives an imperative usage directive. Every word earns its place.

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 tool with one well-documented parameter, an informative output-carrying description, and no output schema, this is adequately complete. It covers what the tool does, what it returns (content of digest), and when to call it. The only minor gap is not describing error/edge cases (e.g., empty project, invalid CSN), but for a context-gathering tool this is a reasonable level of detail.

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 100% for the single parameter (projectPath), and the schema already describes it as 'CAP project root path'. The description doesn't add additional meaning about the parameter beyond what the schema states, landing at the baseline 3 given full schema coverage.

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 ('Compiles the real project to CSN and returns a digest') and clearly states the resource ('existing model: services, entities, fields with types and keys, associations and compositions'). It distinguishes from siblings by framing itself as the pre-generation context-gathering tool, which complements rather than overlaps with generator tools like cap_scaffold_entity.

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 explicitly states WHEN to use it ('Call it BEFORE generating code') and WHY ('so you reuse what exists instead of inventing fields or entities'). This creates a clear usage directive that no other sibling tool claims, giving the agent actionable guidance on sequencing.

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