eval_run

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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: what metrics are used (staleness, conflicts, superseded) and the optional gate outcome. No mention of authentication or rate limits, but sufficient for a read-only evaluation tool.

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?

Every sentence serves a purpose: main action, scoring details, optional behavior, parameter summary, return format. No filler or redundancy. Front-loaded with the primary function.

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 simplicity (one optional parameter, read-only, outputs JSON), the description adequately covers what the tool does and what it returns. Lacks only explicit comparison to siblings for full contextual completeness.

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 has 0% description coverage, but the tool description fully explains the single parameter 'min_score': its optional nature, purpose (threshold), and effect (returns pass/fail gate result). This adds significant value beyond the schema's bare type definition.

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?

Describes a specific verb ('Run') on a clear resource ('memory health evaluation'), with detailed scoring criteria (staleness, conflicts, superseded memories) that distinguishes it from sibling evaluation tools like eval_baseline_create or eval_gate.

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?

States the primary use case and optional CI gate behavior, but does not explicitly compare to siblings like eval_gate or explain when not to use this tool. Implicit guidance is present but not comprehensive.

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