codefmt

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

Beyond the readOnlyHint=true annotation, the description discloses substantial behavior: answers are grounded in codefmt's own content, returned with cited source URLs and a confidence score (0-1 weighted toward rarer terms), and refused rather than hallucinated when the match is too weak. This is far richer than the annotation alone and fully consistent with it.

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 dense and mostly front-loaded, with scope information first and behavioral constraints second; every clause carries useful information. However, it is a single long running sentence — a two-sentence structure would be easier for an agent to parse.

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 one parameter and no output schema, the description carries the full burden of explaining the return: a grounded answer, cited source URLs, a confidence score with a precise definition, and the refusal mode. Nothing essential to invoking the tool or interpreting its result 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% for the single query parameter, which is already defined as 'the natural-language question about codefmt'. The description adds no additional parameter-level meaning (format, length, examples, constraints), so the baseline of 3 is appropriate: schema does the heavy lifting and the description does not compensate further.

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 concrete action and resource: ask a natural-language question about codefmt, specifically its formatting and linting scope (JavaScript, Python, HubL, automation platforms). Its scope is explicit enough that an agent can distinguish it from the sibling formatting tools format_code and format_json without inspecting either 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?

It gives clear routing context: the tool answers on-topic questions about codefmt formatting/linting for the listed languages and platforms, and off-topic or too-weakly-matched questions are refused rather than guessed. It does not explicitly name sibling tools or state 'use format_code instead for execution', so it stops short of a full when-to-use versus when-not-to-use treatment.

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?

Beyond the readOnlyHint annotation, the description reveals non-obvious behavior: it wraps source in platform-specific runtime shells so top-level await, bare return, and injected globals don't break formatting. It also states the return payload is formatted code plus lint diagnostics, which is valuable because no output schema exists.

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 with no filler. The main action and scope are front-loaded, the runtime-wrapping detail earns its place, and the return behavior is stated clearly. Every sentence contributes essential 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?

The description covers supported languages/platforms, the key formatting behavior, and return values despite having no output schema. It is missing explicit guidance on how HubL relates to the language and platform parameters and does not mention alternatives, but the core calling context is sufficiently 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?

Since schema description coverage is 100%, the baseline is 3. The description adds meaning by explaining why code may contain top-level await or bare returns and that platform determines the runtime shell. This goes beyond the schema's parameter descriptions, though the HubL/language mismatch keeps it from being fully precise.

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 ('Format and lint') and a clear resource ('JavaScript, Python, or HubL code for Zapier, n8n, Pipedream, Make, or HubSpot'), which distinguishes it from the JSON-focused format_json. However, it lists 'HubL code' while the input schema's language enum only supports javascript and python, creating a mild ambiguity about how HubL is selected.

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 establishes clear context: use this for JS/Python/HubL code destined for specific automation platforms. It does not explicitly state when not to use it or mention alternatives such as format_json, but the platform/language scope is concrete enough to guide selection.

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 readOnlyHint=true (safe read operation). The description adds valuable behavioral details beyond annotations: number literals are preserved exactly (64-bit safe) and parse errors report exact line and column. 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?

The description consists of two concise sentences that front-load the core action (format JSON), then add key behavioral traits. Every sentence is purposeful 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?

For a simple 3-parameter tool with no output schema, the description covers the main functionality, error behavior (parse errors), and a notable edge case (64-bit number safety). Sibling tools exist but do not demand more detail. The description is fully 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 3 is appropriate. The description adds minimal parameter insight beyond the schema—it mentions 'optionally sorting object keys' (sort_keys) and 'pretty-print or minify' (indent), which are already documented in the schema. No additional semantic depth.

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 it formats a JSON document (pretty-print or minify), with optional sorting of keys. This verb+resource combination is specific to JSON, distinguishing it from sibling tools ask_codefmt and format_code, which likely handle other code formats.

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 this tool is for JSON formatting, and siblings likely cover other languages/formats, but it does not explicitly state when to use this versus ask_codefmt or format_code. No when-not or alternative guidance is provided, leaving the agent to infer usage.

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