The Bridge Stack — one stack, every LLM linked

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

With no annotations, the description carries the full burden and does disclose the key behavioral trait: a Bearer token is required, and the exact fields returned. It does not state that the call is read-only/non-mutating, nor anything about failure modes (expired token, missing auth) or rate limits. Adequate but not rich.

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?

One compact sentence with the returned data front-loaded and the auth requirement trailing, which is the right order. The field list is terse noun fragments rather than full clauses, but nothing is wasted or repeated.

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?

For a zero-parameter, non-mutating read with no output schema, the description supplies what an agent otherwise lacks: the shape of the returned data and the auth requirement. Only error behavior and the read-only nature are left unstated, which is a minor gap at this complexity level.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The description correctly implies a no-argument call by mentioning only an auth header rather than any input fields.

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?

Names the resource (Bridge Stack account) and enumerates the fields returned (tier, expiry, provider spend, spend cap), so an agent knows exactly what data it yields. It reads as a status/read tool without an explicit verb, and it does not reference the siblings bridge_promotion_verdict or bridge_scoreboard, but those serve clearly different purposes so confusion is unlikely.

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?

Usage is only implied: an agent would call this to check account tier or spend state. There is no explicit when-to-use or when-not, and no alternatives named. The one concrete guidance given is the auth prerequisite ("Requires your Bearer token"), which is useful but not a usage rule.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the operation is read-only, requires a Bearer token, and that promotion is a separate POST endpoint, but it does not describe error behavior, rate limits, or the response structure beyond the verdict values.

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?

Two compact sentences with the verdict values front-loaded, followed by read-only and auth context. There is no wasted text.

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?

For a simple two-parameter read tool with no output schema and no annotations, the description covers purpose, read-only behavior, auth, possible verdicts, and the promotion alternative. It remains incomplete on parameter formats and response details, which matters given 0% schema description coverage.

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 must compensate for both parameters. It only conceptually maps provider to 'candidate provider' and task_type to 'task type'; it does not explain expected formats, valid values, or whether provider is an ID or name.

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 states a specific resource and outcome: a promotion-gate verdict for a candidate provider on a task type, including the possible verdict values. It is clear what the tool returns, though it does not explicitly differentiate itself from siblings bridge_account_status and bridge_scoreboard.

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 implies the tool is for checking a promotion verdict and explicitly notes that promotion itself happens via POST /promote, which is useful when-not guidance for the mutation action. However, it gives no guidance on when to use this versus the sibling status or scoreboard tools.

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

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

With no annotations, the description must carry the behavioral burden. It does disclose the access prerequisite (Pro tier and above) and the authentication requirement (Bearer token), which are genuinely useful. It does not state that the operation is read-only, whether results are cached/paginated, or what the snapshot contains, leaving meaningful gaps for a tool with zero annotation coverage.

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?

Two short clauses, front-loaded with the resource and scope, followed by the access constraints. Every sentence earns its place and nothing is wasted.

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?

For a zero-parameter read tool, the description covers scope, tier, and auth, which may be enough to call it correctly. But there is no output schema and the description does not characterize the return value beyond 'scoreboard snapshot', so an agent cannot anticipate the metric fields or shape of the response. Adequate but with a clear gap around result content.

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 tool takes zero parameters, so per the rubric the baseline is 4. The description does not need to explain inputs, and it adds the contextual fact that results are scoped to the caller's account, which is the only input-like dimension that matters here.

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 resource and scope: a per-(model, task_type) scoreboard snapshot for the caller's account. That is far more concrete than the bare name 'bridge_scoreboard' and distinguishes it from siblings like bridge_account_status and bridge_promotion_verdict by content. It stops short of explicitly contrasting with those siblings, so it is not a 5.

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 supplies two important usage conditions: Pro tier or above, and a Bearer token. However, it never says when to call this versus bridge_account_status or bridge_promotion_verdict, nor does it state exclusions. Usage is implied by the tier/auth constraints but not framed as guidance.

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