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

Annotations already cover read-only/idempotent safety, and the description adds real context beyond them: the feed is free with no payment required, results are ordered newest-first, and rejected candidates include the failing gate reason. It does not contradict any annotation. Missing only things like pagination or volume limits.

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 load-bearing facts are front-loaded, but the description is padded with promotional and philosophical asides ('the forge's failures are part of the record, never hidden', 'never silently self-tuned') that add length without helping an agent decide or call. Roughly a third of the text could be cut with no loss of operational meaning.

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?

An output schema exists, so return shape need not be explained, and the description still covers content, filtering, ordering, and access terms. What's missing is guidance on result volume or whether the unfiltered feed is paginated, which matters for a tool that is explicitly read-only and open-world.

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 0%, but there is a single parameter whose enum values are spelled out in the description ('status (candidate | active | superseded | rejected)') and whose filtering behavior (all results when omitted) is explained. That is adequate semantics for one enum param, though the values themselves are not defined individually.

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?

States a specific verb and resource ('the release feed: every intelligence release with its measured deltas AND its rejections') and enumerates the payload fields (version, parent, status, dataset window/hash, walk-forward evaluation, four promotion gates). This is clearly distinguishable from siblings like tollbridge_get_intelligence or tollbridge_lineage, which are not described as full proof-feed enumerations.

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?

It gives one concrete usage rule — 'Filter with `status`; without a filter the whole feed serves, newest first' — which is genuinely actionable. However, it never states when to choose this over related siblings (e.g. tollbridge_get_intelligence, tollbridge_decision), so routing guidance is implied at best.

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