edgegate_compare_runs

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

No annotations exist, so the description carries the full burden. It discloses the output components (gate flips, verdict types) and the auto-selection of the most recent PASSED run when baseline_run_id is omitted. It does not state whether the operation is read-only or any side effects, but the nature of a diff strongly implies non-mutating behavior. The explicit baseline fallback behavior is valuable transparency that exceeds basic expectations.

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 two sentences, efficiently packed with useful information: the operation, the output list, and the default baseline behavior. No filler or redundant phrasing. Front-loaded with the verb 'Diff' and resource, making it immediately 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?

No output schema exists, so the description must explain the return values—and it does, listing metrics delta, gate flips, per-device breakdown, and the verdict categories. It also covers the key baseline selection logic. It lacks mention of permissions, errors, or pipeline requirements, but for a comparison tool with moderate complexity, this is a solid, usable description.

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 67%: run_id and baseline_run_id have descriptions, while workspace_id lacks one. The description adds context on overall tool behavior but does not provide new parameter-level details beyond the schema. In fact, the schema's baseline_run_id description includes the fallback to 'most recent completed run' which the main description omits. The description is adequate but does not meaningfully supplement the schema.

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 starts with a specific verb and resource: 'Diff two EdgeGate runs in the same pipeline.' It enumerates exact outputs (metrics delta, gate flips, per-device breakdown, overall verdict) which clearly distinguishes it from siblings like edgegate_check_status or edgegate_get_report. This is a textbook example of a purpose that is both specific and differentiated.

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 gives clear context: this tool is for comparing runs in the same pipeline, with a defined default behavior for missing baseline_run_id. It does not explicitly name alternatives or exclusions, but the purpose is so distinct that an agent can intuitively know when to use it. Missing explicit 'use when' or 'not when' guidance lowers it one point.

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