Forecall Failure KB

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

Annotations only declare readOnlyHint=false, idempotentHint=false and openWorldHint=false; the description adds cost behavior ('takes no units; only the key's per-minute rate limit applies'), call cardinality, and the fact that it mutates verification state. These are exactly the traits an agent needs beyond the annotation flags, and they are consistent with idempotentHint=false.

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?

Four tight, front-loaded sentences with no filler; the core action and the exclusion come first. The trailing 'Returns the record's new state' is largely redundant given that an output schema exists, which costs it the top mark.

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?

Given an output schema exists, the description need not explain return values, and it covers everything else: when to call, when not to, the alternative, call frequency, and cost. Nothing an agent needs to invoke this correctly is missing.

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 100%, so record_id, lookup_id, env and evidence are already documented in the schema; that sets the baseline at 3. The description adds a useful gloss on the `inapplicable` enum member, but says nothing about lookup_id linkage or the env payload, so it does not meaningfully exceed 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?

States a specific verb and resource ('Report the outcome of applying a workaround you obtained from kb_lookup') and enumerates the three accepted outcomes. It clearly distinguishes itself from kb_report and kb_dispute, which appear as siblings, so an agent can route correctly without opening any schema.

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?

Gives explicit trigger conditions ('Call it once per record you tried'), an exclusion ('Do not use it for a failure you fixed another way'), and names the alternative to use instead (kb_report). It even clarifies the ambiguous case where the predicted failure never occurred.

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?

Annotations already declare readOnlyHint=false, openWorldHint=false, and idempotentHint=true. The description adds useful operational context beyond annotations: 'It takes no units; only the key's per-minute rate limit applies' and 'Returns the dispute's id.' It does not disclose visibility or downstream effects of a dispute, but covers enough for safe invocation.

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?

Front-loads the core action, then usage conditions, then the exclusion and alternative, then operational notes. Every sentence serves a distinct purpose: what it does, when to use, when not to use, rate-limit context, and return value. No wasted words.

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 3-parameter tool with full schema coverage, annotations, and an output schema, the description supplies all the missing routing and operational context: when to use, when not to use, the alternative tool, rate-limit behavior, and the return value. An agent has everything needed to call it correctly.

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 100%, so all three parameters are already documented in the schema. The description's phrase 'optionally pointing to a better record' maps to alternative_record_id but adds no syntax, format, or constraint details beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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: 'Flag a record as wrong or outdated, optionally pointing to a better record.' Explicitly distinguishes from sibling kb_report by stating 'Do not use it to report a new failure: use kb_report.' An agent can identify the tool's scope without opening the schema.

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?

Gives explicit when-to-use conditions (after a kb_lookup workaround failed for a non-environment reason, or the record describes the wrong failure) and an explicit when-not (not for new failures). Names the alternative tool (kb_report) and the condition that selects it.

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?

Annotations cover the safety profile (readOnly, idempotent, closed-world), and the description adds real operational context beyond them: each call consumes one unit of a monthly quota, results are capped by max_results, verified records are surfaced before unverified ones, and preflight may legitimately return nothing. The quota disclosure in particular is information an agent cannot get from structured fields.

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?

Four dense sentences ordered purpose → when to use → what comes back/cost → exclusions. Nothing is padding and the most decision-relevant routing rule (preflight mode) is front-loaded.

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 the description need not enumerate return fields, yet it still flags the verified/unverified ordering and the empty-result possibility. For a 9-parameter tool with nested args_shape, an agent has everything needed to invoke it correctly.

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 100%, so the baseline is 3, but the description adds functional meaning: it explains the lookup vs preflight split and that preflight requires args_shape, tying the parameters to a workflow rather than just restating types.

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 opens with a specific verb and resource — 'Check for known failures and workarounds' — and scopes it to third-party tool calls. It is unambiguous what the tool returns (workarounds, verified first), though it never explicitly contrasts itself with the kb_confirm/kb_dispute/kb_report siblings.

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 concrete triggers ('a tool call errored, returned an unexpected shape, or you are about to call a tool you have not used in this session'), tells the agent to switch mode to preflight in the second case, and states two explicit exclusions (non-tool-call questions, tools of this server).

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?

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=false, idempotentHint=false) by disclosing server-side redaction of secrets/paths/ids, a write path, a rate limit (100 reports/day per key), cost (no units), and post-write state semantics (record starts unverified until others reproduce it). It also warns what must not be included, which directly shapes safe invocation.

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?

Front-loaded with purpose and the first-use condition, then procedurally ordered guidance. It is dense but each sentence carries operational information; the mixed-register asides ('it takes no units') and run-on pacing keep it from a 5.

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 10-parameter, nested-schema write tool with an output schema, the description covers selection, timing, exclusion, input constraints, cost, rate limits, and return semantics. Nothing an agent needs to call it correctly is missing.

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 100%, so the baseline is 3; the description adds real value by specifying what error_text should contain ('as returned'), what workaround should capture ('the workaround that worked, e.g. pass the key as the api_key argument'), and a critical prohibition on raw payloads and argument values. It stops short of explaining several optional params (lang, notes, lookup_id, error_class) beyond what the schema already says.

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 ('Report a tool-call failure you resolved') plus the downstream benefit ('so other agents can skip it'). It is clearly separable from the sibling tools kb_lookup/kb_confirm/kb_dispute, which are named explicitly.

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?

Gives explicit preconditions ('Call only after the workaround actually worked, and once per failure') and explicit exclusions ('Do not use it for failures of your own code, or for ones a kb_lookup already knew: confirm those with kb_confirm instead'), naming the correct alternative tool for each excluded case.

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