Topos Code Evaluation

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral details such as progress streaming, pagination, the rollup taking the minimum per dimension, and path resolution constraints. No contradictions.

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 a single, well-structured paragraph of 5 sentences. It is front-loaded with the primary purpose and efficiently covers all key aspects without 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 tool's complexity (multiple languages, rollup, pagination, many parameters), the description covers the main points: purpose, usage context, behavioral traits, and return format without an output schema. Slightly lacking in full detail of the output structure but sufficient.

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 100%, so the description adds little beyond what the schema already provides. While the description gives context like 'weakest file floors it' for the rollup, this is more behavioral than parameter-specific. Baseline 3 is appropriate.

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 clearly states that the tool recursively scores source files on a SIMPLE/COMPOSABLE/SECURE lattice with a project rollup. It distinguishes from siblings by specifying whole-tree usage versus single file or snippet tools.

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?

Explicit guidance is given: use for a whole tree, for single file use topos_evaluate_file, for snippet use topos_evaluate_code. Additional context includes language autodetection, skipping unsupported files, and exempting entrypoint modules.

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