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

Annotations already establish the safe read-only/idempotent profile, so the bar is lower. The description still adds meaningful context beyond them: it declares the output is a bounded projection with no model bytes, no persistence, and no execution, and warns that result digests prove consistency rather than server attestation — a trust caveat not derivable from the annotations.

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?

Three compact sentences, front-loaded with the component scope and followed by exclusions and the digest caveat. No filler, though the phrasing is jargon-heavy enough to reduce immediate readability.

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?

With an output schema present, return values need not be explained, and the description does cover scope and trust boundaries. But for a tool whose sole input is a large nested object, it omits how the 'result' payload is produced and how it relates to sibling query/publish tools, leaving the workflow incomplete.

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 single top-level 'result' parameter has 0% schema description coverage, and the description says nothing about what it must contain or how it is obtained (presumably echoing a prior call). While some deeply nested fields carry their own schema descriptions, the description does not compensate for the undocumented top-level input.

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 names a specific verb ('validates and returns') and resource ('bounded Evidence IR query projection') and scopes it to 'the same attachment'. However, 'Evidence IR query projection' is dense internal jargon and the description never distinguishes this tool from siblings like deepbom_query_file or deepbom_publish_analysis.

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?

'For the same attachment' implies this is a follow-up call on an artifact already analyzed, and the exclusion list ('no model bytes, state persistence, or runtime execution') sketches boundaries. But there is no explicit when-to-use, when-not, or named alternative among the six siblings.

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