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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is clear. The description adds one meaningful behavioral detail—'without judging the agent's semantic choices'—which clarifies that validation is purely structural. However, the rest of the extra context (the seat, The Wall, sandbox, registry link) is tangential and does not enhance behavioral transparency. The description does not contradict annotations but also does not go far beyond them.

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 core purpose is front-loaded in the first sentence, which is good. But the description then includes a large amount of tangential information: the server name, 'a live seat on The Wall (runs in Rokha's sandbox)', 'Called through their seat; their data comes back as it is.', 'Read-shaped tools only...', and a registry link. These sentences do not aid tool selection or invocation. The description is overlong relative to its actual content, warranting a mid score.

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 tool is complex: two nested object parameters, no output schema, and no parameter descriptions. The description does not explain what the function returns on success/failure, how to interpret the validation result, or what constitutes valid evidence versus invalid. It also leaves the meaning of 'active verified catalog' and 'canonical selection-evidence sidecar' unspecified. For such a complex validation tool, the definition is insufficiently complete for an agent to call it confidently without further context.

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 carries the full burden of explaining parameters. It identifies 'evidence' as a 'canonical selection-evidence sidecar' and 'manifest' as a manifest object, which adds minimal meaning. However, it does not describe the required structure, content, or semantics of either object beyond what the schema already shows (and the schema itself lacks descriptions). The phrase 'active verified catalog' is also undefined. With two object parameters and zero schema descriptions, this is inadequate—an agent would not know how to construct the 'evidence' object or what the validation checks.

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 clearly states a specific verb ('validate'), a specific resource ('canonical selection-evidence sidecar'), and the targets ('a manifest and the active verified catalog'). It also clarifies what it does not do ('without writing files or judging the agent's semantic choices'), which distinguishes it from sibling tools like export_selection_evidence and diff_stack. No ambiguity remains about the tool's core operation.

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 does not explicitly state when to use this tool versus alternatives. It mentions 'without writing files or judging the agent's semantic choices', implying it is for validation only, but it never names sibling tools or contrasts its role (e.g., vs. export_selection_evidence). The generic server-level note 'Read-shaped tools only' applies to all tools in the server, not this one specifically, and offers no routing guidance. An agent would have to infer usage context from the tool name and description alone.

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