blacksmith_cost_trend

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

With no annotations provided, the description carries the burden of disclosing behavior. It explains that the tool compares compute and sticky-disk costs over months and highlights patterns, which adds useful context. However, it does not mention that this is a read-only operation, nor does it describe the return format or how data is aggregated, leaving some ambiguity.

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, front-loaded sentence that conveys the core purpose and a key analytical use. It contains no filler or redundant information, making it highly efficient.

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?

The tool has no output schema and no annotations, so the description should ideally convey the shape of the result. It does imply a multi-month comparison but does not specify whether the output is a time series, a summary table, or a visual representation. The two optional parameters are well covered, but the lack of return-value detail leaves a notable gap for an agent invoking the tool.

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?

The description says 'for the last N months', which directly maps to the 'months' parameter and gives semantic meaning beyond the schema's default and range. The 'org' parameter is described in the schema with its environment variable default, so the description does not need to repeat it. Since schema coverage is only 50%, the description compensates for the undocumented 'months' parameter.

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 provides month-over-month compute vs sticky-disk cost for a configurable number of months. This differentiates it from sibling cost tools that focus on daily breakdowns, per-repo, or overall summaries. However, it lacks an explicit action verb like 'returns' or 'shows', which makes the purpose slightly less direct.

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 gives clear analytical context: it is meant to spot accumulating cache cost versus one-off compute spikes. This implies the appropriate use case and distinguishes it from other cost tools, though it does not explicitly name alternatives or state when not to use it.

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