save_eval

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

With no annotations provided, the description fully takes on the transparency burden. It discloses that the tool reads from session cache, returns an eval ID with a convergence score, and details persistence behavior (storage path, 100 compact records + 10 full runs per domain). This goes beyond simple 'saves data' and gives the agent a clear model of side effects and persistence.

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 three sentences, each earning its place: purpose/prerequisite, return values, and persistence/history guidance. It is front-loaded with the primary action, avoids redundancy, and maintains a logical flow from what the tool does to how to use it. No filler is present.

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 the tool's moderate complexity and lack of annotations/output schema, the description is remarkably complete. It covers prerequisites, return values, storage semantics, limits, and relationship to a sibling tool. An agent could invoke save_eval correctly and understand the consequences without external documentation.

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 input schema already has 100% coverage with clear descriptions for all three parameters (url, note, save_full_run), so the baseline is 3. The description adds no substantial parameter-level detail beyond what the schema provides; it only contextualizes the overall workflow. It does not repeat or enhance the schema's parameter explanations.

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 opens with a clear verb-resource pairing: 'Save the current roundtable or audit persona results for a URL to the eval store.' This distinguishes save_eval from sibling tools like list_evals (which reviews history) and merch_roundtable (which produces the results). It accurately states the tool's core function without ambiguity.

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 explicitly states the prerequisite: 'call merch_roundtable or audit_storefront first on the same URL.' It also directs users to list_evals for reviewing history, creating a clear when-to-use versus alternative-tool distinction. This gives concrete context for when save_eval is appropriate and what must occur before invoking it.

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