FAHCE Integrity Repair

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description discloses two non-obvious behaviors: it stores an immutable receipt (a persistence side effect) and meters one logical determination (a cost/accounting unit), plus the negative guarantee that no external repair is executed. That is real added context, though it omits whether the call fails or degrades when metering limits are hit.

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 sentences, front-loaded with the diagnostic scope and followed by the side-effect/negative-guarantee clause. No filler, no repetition of the tool name, every clause carries information.

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 tool with a nested request object, a 512 KiB body ceiling and an output schema already documenting return values, the description covers purpose, side effects and the no-repair guarantee adequately. The remaining gap is the missing routing relative to its three sibling tools and the evidence requirements.

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 only 50%, and the description supplies essentially no parameter meaning: it never explains the required evidence array, the schema constant, or the optional idempotency_key (despite the tool being idempotent). Only "candidate output" is echoed from the schema, so the description does not compensate for the coverage gap.

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 ("Diagnose") and resource ("a candidate output") and enumerates the exact defect classes checked: unsupported claims, contradictions, wrong attribution, stale authority, unsafe execution claims. It implicitly separates itself from the repair siblings by stating it "does not execute an external repair," but never names fahce_integrity_repair_bundle, fahce_plan_bounded_repair, or fahce_verify_repaired_output, so an agent must infer the boundary.

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: by saying it stores a receipt and does not perform repair, the description suggests this is the diagnostic step preceding repair. There is no explicit when-to-use statement, no condition that selects it over fahce_verify_repaired_output or fahce_plan_bounded_repair, and no prerequisites (e.g., evidence must be supplied) spelled out.

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, idempotentHint=true and destructiveHint=false; the description goes further by explaining WHY it is not read-only ('stores an immutable receipt and meters one logical determination') and clarifies the non-action boundary (no external repair). This reconciles the non-read-only hint with a non-destructive profile, adding genuine context beyond the 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?

Two tightly written sentences: the first front-loads what is returned, the second covers behavioral scope and metering. Every clause earns its place with no redundancy or filler.

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 is not obligated to explain return values, and it adequately covers output shape plus receipt/metering behavior. The remaining gap is the lack of routing guidance against its three siblings and any note about the request body, which keeps it short of complete.

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 description says nothing about the two parameters: not the required nested 'request' object, its schema/candidate_output/evidence structure, nor the idempotency_key. With schema description coverage at only 50%, the description is expected to compensate and does not, leaving the agent to rely entirely on 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?

The description names a specific verb plus the exact resources returned (diagnosis, bounded repair plan, verification state, receipt) and characterizes the response as machine-readable. An agent can tell it is the combined bundle, but the three sibling tools are never named, so the distinction is inferred from the tool name rather than stated.

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 phrase 'in one machine-readable response' implies this is the all-in-one variant versus the three granular siblings, and 'does not execute an external repair' sets a scope boundary. However, it never explicitly states when to pick the bundle over fahce_diagnose_integrity / fahce_plan_bounded_repair / fahce_verify_repaired_output.

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 non-read-only, non-destructive, and idempotent behavior. The description adds genuinely new context: the plan never claims execution or verification, an immutable receipt is stored, and one logical determination is metered. That is useful behavior beyond the annotations, though it doesn't disclose what the receipt contains or what gets returned.

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 tight sentences, no filler. The first sentence states the purpose, the second the non-claim scope, and the third distinguishes storage/metering from execution. Naturally 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?

For a complex tool with a nested schema and an output schema, the description covers scope and side effects but omits workflow positioning relative to its three siblings and does not explain what the plan output looks like. The output schema fills some of that gap, but the routing context 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 coverage is 50%, and the description adds essentially no information about the 'request' or 'idempotency_key' parameters. The rich nested schema descriptions carry the semantic load; the description only adds the abstract notion of 'evidence-preserving', which loosely maps to the evidence field.

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 verb and artifact — 'produce a bounded, evidence-preserving repair plan for an integrity failure' — which is distinct from the sibling fahce_integrity_repair_bundle. However, it doesn't explicitly contrast itself against fahce_diagnose_integrity or fahce_verify_repaired_output, so the reader has to infer the boundary between planning, diagnosis, and verification.

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 implies a use case ('for an integrity failure') but never states when to choose this over fahce_diagnose_integrity or fahce_verify_repaired_output, nor when a caller should not use it. With three sibling tools and no routing language, an agent must guess where this fits in the workflow.

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 the write (readOnlyHint=false), idempotency and non-destructive/closed-world profile. The description adds genuinely new behavioral facts: the receipt is immutable, the call 'meters one logical determination' (a quota/billing implication), and it does not perform external repair. It omits any statement on auth requirements or whether re-verification of the same candidate re-meters.

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 sentences, front-loaded with the core action and deliverable, with the scope-boundary and metering caveats trailing. No filler or redundancy.

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 describe return values, and it conveys what the operation stores and meters plus its non-repair boundary. Remaining gaps are the absence of any parameter/evidence guidance and idempotency behavior, which matter for a nested, evidence-driven request.

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 description says nothing about either parameter. Only 50% of the schema carries descriptions (candidate_output and expected_output), while the request envelope, the evidence array structure, and idempotency_key (whose semantics are directly relevant to the idempotentHint annotation) are not explained in the description.

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 (recheck/verify) and resource (a repaired candidate output) and names the deliverable (a deterministic, scoped verification receipt). It implicitly fits the pipeline after repair, though it never names the sibling tools (fahce_diagnose_integrity, fahce_plan_bounded_repair, fahce_integrity_repair_bundle) to disambiguate.

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 phrase 'Recheck a repaired candidate' establishes the post-repair context, and the closing clause 'it does not execute an external repair' draws a clear boundary against the repair operation. No explicit when-not conditions or named alternatives are given, so it falls short of a full 5.

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