json-sanity

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

Annotations provide safety profile (readOnlyHint, idempotentHint), and description adds detail on specific repairs attempted. No contradiction with 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?

Single sentence with front-loaded action and list of repair targets; no redundant 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?

Adequate for core purpose but missing behavior on repair failure (returns original? error?), and no mention of return format despite lacking output schema.

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 covers 100% of parameters, so baseline is 3. Description does not add meaning beyond schema (e.g., does not explain api_key_id purpose or json_string format).

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?

Description uses specific verb 'repair' and lists concrete issues (trailing commas, single quotes, etc.), clearly distinguishing from siblings like 'validate_json' and 'repair_string'.

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?

No explicit guidance on when to use this tool vs alternatives (e.g., 'validate_json' for checking validity first), nor any when-not-to-use conditions.

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?

The description fully discloses behavioral traits beyond the annotations: deterministic processing, markdown fence stripping, regex prose removal, control character escaping, validation with fallback repairs, and optional schema validation. Annotations already indicate read-only, idempotent, non-destructive behavior, and the description aligns without contradiction.

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 description is concise at 3 sentences, packed with information. It opens with the core purpose ('Deterministic repair engine') and lists steps in a structured manner. No superfluous text, but minor improvement could be bullet points for 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?

Given the lack of an output schema, the description adequately explains the input processing and expected outcome (repaired JSON). It does not explicitly describe the return format, but the steps imply what the output will be. The presence of sibling tools provides context, making the description sufficient for selecting this tool.

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 input schema covers 100% of parameters, and the description adds value by explaining that the optional 'schema' parameter triggers validation and translates errors into 'Fix Action' strings. This goes beyond the schema description, though the 'raw_string' and 'api_key_id' are already well-described in 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 clearly states the tool's purpose: a deterministic repair engine for raw LLM output containing JSON. It enumerates specific steps (stripping fences, escaping characters, validation) and differentiates from siblings like validate_json by focusing on repair rather than just validation.

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 implicitly defines when to use the tool ('Given a raw LLM output that should contain JSON'), but it does not explicitly contrast with sibling tools or provide criteria for when not to use it. The usage context is clear but lacks explicit exclusion guidance.

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 indicate read-only and idempotent; description adds specific behaviors (removing prose, fixing control characters). No contradictions.

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, no fluff, front-loaded with action and context. Every word earns its place.

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?

Covers purpose, scenario, and basic actions. Lacks output description or error handling, but for a simple sanitization tool it is adequate.

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 baseline is 3. Description provides no additional parameter meaning beyond what the schema already describes.

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?

Clearly states it sanitizes JSON by removing prose and repairing control characters, with a specific use case. However, does not explicitly distinguish from sibling tools like repair_json or validate_json, but the verb 'sanitize' and specific actions are clear.

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?

Explicitly tells when to use ('before saving to session/state') and why (prevent errors/poisoning), but does not mention when not to use or compare to alternatives.

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=true and idempotentHint=true. The description adds that it returns a parsed object on success, providing behavioral context beyond annotations. No contradictions.

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, no wasted words. The first sentence states the purpose, the second describes the return. Perfectly 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 validation tool without output schema, the description mentions the return type but omits behavior on invalid JSON (e.g., error throwing). The api_key_id parameter seems unrelated, adding confusion. Adequate but gaps remain.

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% with both parameters described in the schema. The description does not add additional meaning beyond what the schema provides. Baseline 3 is appropriate.

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 clearly states 'Check whether a JSON string is valid' (specific verb+resource) and 'Returns parsed object on success'. This distinguishes it from sibling tools like repair_json and sanitize_json_output, which handle different operations.

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 use for validation but does not explicitly state when to use this tool vs alternatives (e.g., repair_json for fixing, sanitize_json_output for cleaning). No when-not or context provided.

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