Topos Code Evaluation

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds context: that COMPOSABLE requires a dependency graph, that SIMPLE/SECURE always run, and that the tool returns an EvaluationResult. No contradictions found.

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?

Three sentences, no filler. First sentence states core purpose and uniqueness. Second explains usage and dependencies. Third gives alternatives and a key condition. Well front-loaded.

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?

Without an output schema, the description mentions returning an EvaluationResult but doesn't detail its structure. It covers the lattice, graph dependency, and conditions for COMPOSABLE. Could mention error cases or more return details, but overall sufficient for the complexity.

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 baseline is 3. The description does not elaborate on individual parameters beyond the schema. It indirectly explains gitnexus_dir's role in achieving COMPOSABLE, but this is marginal added value.

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 'Score a file on disk on the SIMPLE / COMPOSABLE / SECURE lattice' and distinguishes itself as 'the only evaluate tool that can reach COMPOSABLE (read-only)'. It also explicitly names sibling alternatives: topos_evaluate_code for in-memory snippets and topos_evaluate_project for whole directories.

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?

Usage is explicitly stated: 'Use for one file on disk.' It provides prerequisites (dependency graph generated with topos_generate_depgraph, which needs npm install) and contrasts with other evaluate tools for different contexts. The condition 'coupling_available is false when no graph is found' further guides when COMPOSABLE is unreachable.

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