topos_evaluate_project

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

Annotations already indicate readOnlyHint=false, but the description goes far beyond that: it discloses the specific side effect of generating/refreshing `.gitnexus`, the behavior of skipping unsupported files, the rollup taking the project-wide minimum, and the graceful degradation when generation is not possible (`coupling_available`/`warnings`). This is exactly the kind of contextual detail that helps an agent predict side effects.

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 information-dense with five sentences, each addressing a distinct concern: main purpose, language autodetection, rollup semantics, return values/pagination, and side-effect behavior. It is front-loaded and free of filler, though the final sentence is long and packs multiple clauses. For a complex tool with 9 parameters, this density is warranted.

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?

With no output schema, the description compensates by explicitly naming the returned lists (`hard_fails`, `leaf_composable_zeros`, `maintainability_giants`) and describing the paginated per-file table with gate failures first. It also covers side effects, failure fallback, and parameter-triggered behavior. Together with the heavily documented schema, the description provides a complete operational picture.

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%, so the schema already documents each parameter. The description adds value by explaining how `no_composable` controls the .gitnexus generation workflow, how `limit`/`offset` drive pagination, and how `gitnexus_dir` relates to project-root behavior. This goes beyond the schema's per-parameter descriptions and links them to the overall execution model.

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+resource+scope: 'Recursively score every supported source file in a directory' on the four-dimension lattice. It explicitly lists supported languages, notes autodetection with no language argument, and distinguishes itself from file-level evaluation by referencing `topos_evaluate_file`.

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 makes clear this is for whole-directory evaluation and even mentions `same as topos_evaluate_file` for .gitnexus generation, which implicitly contrasts it with the file tool. However, it never explicitly states when to use this vs a sibling (e.g., 'use topos_evaluate_file for a single file'), so the guidance remains implied rather than directly articulated.

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