get_eda_findings

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

With no annotations, the description carries the full burden and does well: it discloses that the operation reads cached JSON with no recomputation, is cheap, and output size scales with limit. It also explains filter composition and severity values, which goes beyond basic read-only behavior.

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 compact and well-structured, with each line adding substantive information: what it fetches, how filters combine, severity values, paging, cost behavior, and output size. No redundant or filler content.

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 description covers purpose, usage context, behavioral characteristics, filtering, and paging. With an output schema present, return values are already accounted for. Minor gaps remain: no explicit comparison to alternatives and some parameter semantics (column/category) are not fully addressed, but overall it is sufficient for an agent to select and invoke confidently.

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%, so the description must compensate for parameter meanings. It explains severity values, offset/limit for paging, and run_id context, but does not clarify the semantics of 'column' and 'category' filters. Some parameters remain underspecified.

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 uses the specific verb 'Fetch' with the resource 'findings from a prior run_eda artifact', clearly distinguishing this as a retrieval tool for prior EDA results. It further specifies 'filtered, paginated view', which precisely defines its function among siblings like run_eda or summarize_run.

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 states the tool operates on 'a prior run_eda artifact', indicating it should be used after running run_eda. It also provides cost guidance ('Cheap — reads cached JSON, no recomputation') and pagination usage ('Use offset/limit to page through'), but does not explicitly name alternatives or when-not-to-use conditions.

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