cost-phase

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

No annotations are provided, so the description must fully disclose behavioral traits. It describes data crossing and inference but does not clarify side effects (e.g., whether persist modifies state), error conditions, or prerequisites. Parameters like refresh_pricing and persist hint at mutability, yet the description leaves their impact ambiguous, which is a significant gap for a tool with no annotation safety cues.

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 moderately concise and front-loaded with the core purpose and data sources, but it is a single dense paragraph without clear separation of concerns (e.g., no parameter breakdown, no usage examples). The trigger list at the end is helpful, but overall structure could be improved for readability.

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 5 parameters, no output schema, and no annotations, the description is incomplete. It lacks details on the return format ('canonical shape'), parameter interplay, and common usage patterns. It does not explain how to use optional parameters like config_dirs or persist, leaving significant gaps for an agent to invoke the tool correctly.

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?

With only 40% schema coverage, the description should compensate for undocumented parameters, but it does not. It explains phase_id conceptually, but config_dirs, refresh_pricing, and persist are not mentioned in the description at all. Users receive no guidance on their meaning or typical values beyond the minimal schema hints.

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 the tool correlates cost with a specific phase of the kit-mcp framework, detailing data sources (mtime, completed_at, git log) and output (canonical shape with confidence levels). It differentiates from ccusage via workflow context and lists trigger phrases, making the purpose highly specific and distinguishable from sibling tools like cost-session or cost-today.

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 provides trigger phrases ('custo da fase', 'phase cost') indicating when to use, but does not explicitly state when not to use or compare against all relevant siblings (e.g., cost-session, cost-today). The mention of 'Diferencial vs ccusage' offers some context, but it's not a thorough guideline for agent decision-making.

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