stackledger

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

With no annotations, the description carries the full burden and does fairly well: it discloses the estimation basis ('category price ranges, not vendor-specific claims'), the auto-recognition behavior for common tools, and that category is optional. It stops short of stating permissions, limits on list size, or whether the operation is side-effect free, which keeps it out of the top band.

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 core action and input format are front-loaded in the first clause, followed by the analysis outputs and the estimation caveat. It is a single dense sentence plus two short ones, with no filler, though the opening sentence packs several ideas at once.

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?

There is no output schema, so the description must describe the return value, and it does ('Returns a full readable report'). Combined with full input-format specification and the estimation caveat, an agent has everything needed to call this correctly and set expectations about results.

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 baseline is 3, but the description adds genuine meaning beyond the schema: it explains that category is optional and that well-known tools like Slack or Notion are auto-recognized, so the agent understands a shorter input is acceptable. That is real value the schema's example alone does not convey.

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 a specific verb (audit) and resource (a pasted list of SaaS subscriptions), and enumerates exactly what the audit detects: category overlap, overpriced line items, and monthly/annual spend. It also sets expectations on output ('Returns a full readable report'), so an agent knows precisely what this tool produces without opening a schema.

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 implied by the input contract (paste one subscription per line), but there is no explicit when-to-use vs when-not, no prerequisites, and no alternatives named. With no sibling tools to route against, the omission is less costly, but the description still leaves invocation timing to inference.

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