athena_field_get

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

With no annotations available, the description carries the full burden of behavioral disclosure. It does this reasonably well by using 'Fetch' (implying a read operation) and by explicitly listing the contents of the returned FIELDRUN ('frozen module inputs, candidates, metric states, provenance edges and digest'). This gives the agent a clear expectation of the response shape. However, it does not disclose error behavior (e.g., what happens if run_id is not found) or whether the data is historical/point-in-time, which would add further transparency.

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, well-structured sentence that front-loads the verb 'Fetch' and immediately states the object ('one persisted FIELDRUN'). It then efficiently lists the key components without extra fluff. Every word earns its place, making it concise and scannable.

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 simple get-by-ID tool with one parameter and no output schema, the description is largely complete: it states what is fetched and what is included in the result. The terms 'FIELDRUN', 'frozen module inputs', and 'provenance edges' are domain-specific but appear consistently across sibling tools, so an agent familiar with the system will understand. The main gap is the lack of usage context (when to use this vs. alternatives) and any note about the absence of an output schema. Overall, the coverage is adequate for the tool's simplicity.

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 schema provides no description for the single parameter run_id, and schema description coverage is 0%. The description partially compensates by implying that run_id identifies a 'persisted FIELDRUN', which clarifies the parameter's purpose. However, it does not explain how to obtain a valid run_id, its format, or its lifecycle, leaving some ambiguity. The description adds some meaning but not full compensation for the schema's silence.

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 a specific verb 'Fetch' and clearly identifies the resource being fetched: 'one persisted FIELDRUN'. It also enumerates the specific components included (frozen module inputs, candidates, metric states, provenance edges, digest), which helps distinguish it from other tools that might only retrieve a summary or a list. However, it does not explicitly contrast itself with sibling tools like field_recent or field_replay, so it doesn't fully differentiate within the family.

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 no guidance on when to use this tool versus alternatives. It does not mention scenarios where fetching a full FIELDRUN with provenance is appropriate, nor does it note any prerequisites (e.g., run_id must come from a recent list). This is a clear gap, especially given the large number of sibling tools with similar fetch/recent/replay patterns.

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