cost_delta

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

With no annotations, the description carries the full burden, and it does disclose crucial safety context: 'Read-only (v0.2): does not mutate the cache store.' That is a genuinely useful read-only declaration. However, it omits what the comparison output contains, any rate limits, or how cost is computed, so the behavioral picture is partial.

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 prose is fragmented into odd line breaks and phrasing ('The m3 "star-able" number', 'files-accepted vs ChatGPT's 40-file cap') that reads as marketing rather than specification. The read-only constraint, the most actionable fact, is buried at the end instead of 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?

For a two-parameter comparison tool with no schema documentation, no annotations, and no parameter coverage, the description must compensate and does not. It omits what 'repo' and 'model' expect, what triggers the cost computation, and how results are shaped. An output schema exists, so return values need not be explained, but the input contract is left entirely unresolved.

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 0% and neither parameter is documented. The description mentions 'repo' only obliquely via 'equal repo size' and never explains the 'model' parameter or its default empty-string behavior. Both parameters are effectively undocumented, so an agent cannot know what to pass.

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 states the tool compares per-query token cost against Claude Opus at equal repo size, which gives a resource and a comparison dimension. However, it's cluttered with marketing language ('m3 star-able number') and tangential claims (file caps), so the core purpose is muddled. It is distinguishable from query_repo and list_files, but only loosely.

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?

There is no explicit statement of when to use this tool versus query_repo or list_files, nor any precondition (e.g., must a repo already be indexed?). Usage is only implied by 'per-query' and 'equal repo size'. No exclusions or alternatives are named.

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