netcafe-devkit

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds that the diff is computed via LCS, not guessed, conveying determinism and accuracy. This is valuable beyond annotations, though it doesn't cover potential edge cases.

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 primary function, followed by usage context. No wasted words or repetition of schema 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 simple two-string tool with an output schema present, the description covers purpose, usage, and behavioral expectations completely. The existence of an output schema means return format details are already handled structurally.

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%, and each parameter has a clear description ('first (before) text' and 'second (after) text'). The description adds no further semantic detail beyond what the schema provides, so a baseline score of 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 states exactly what the tool does: returns added and removed lines with line numbers, using LCS. It clearly identifies the resource (two texts) and the operation (diff calculation), distinguishing it from any sibling tool.

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 it: 'Use to compare two versions of a config, a document, or any command output.' It also explains the alternative (asking an LLM) and why this tool is better, providing clear guidance on when to choose this tool.

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 burden. It discloses that it validates and pretty-prints, and reports error location on invalid input, which is useful. However, it does not mention whether it modifies input, requires network access, or any side effects. It does not contradict annotations (there are none), and the description is accurate about its core behavior.

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 a single concise sentence, front-loaded with the purpose and a key detail (error location). It earns its place with 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?

The tool has 3 parameters with no schema descriptions, no annotations, and no output schema. The description is too sparse to guide the agent on how to provide input (url vs json), what the output structure looks like, or any edge cases. It covers the basic functionality but lacks sufficient detail for effective invocation.

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%, and the input schema has three properties (url, json, indent) with no descriptions. The description mentions the indent (2-space) but does not clarify the purpose of 'url' or 'json' parameters, nor how they relate (e.g., one or the other?). The description adds minimal meaning beyond the schema, leaving ambiguity.

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 validates and pretty-prints JSON with a 2-space indent, and reports error location if invalid. This distinguishes it from siblings like diff_text, redact_text, and what_can_you_do, though it does not explicitly differentiate from validate_json or json_yaml, but the pretty-print and error location aspects are specific.

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 usage for validating and formatting JSON, but provides no explicit guidance on when to choose this over validate_json or json_yaml. It does not mention when not to use it or alternative tools. The mention of error location could be useful for debugging, but the context is not fully developed.

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 annotations (readOnly, idempotent, non-destructive), the description discloses key behavior: auto-detection of direction ('It works out which one you gave it') and error handling ('A parse failure comes back with the parser message instead of silently producing something that looks fine and is not'). This adds valuable context beyond what the annotations provide.

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 (3 sentences) and front-loaded with the primary action. Each sentence adds distinct value: functionality, auto-detection/error behavior, and usage context. There is no fluff or repetition of schema details.

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 conversion tool with an output schema present, the description is complete. It covers function, behavior on failure, and practical use cases. The annotations and output schema handle safety and return format, so the description doesn't need to repeat those details.

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 has 100% coverage with descriptions for both parameters ('to' and 'text'). The description adds context about auto-detection and that the direction parameter is optional, but it doesn't provide additional syntax or semantics beyond the schema. This meets the baseline for well-documented schemas.

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 exact function: 'Converts JSON to YAML or YAML to JSON.' It also highlights auto-detection of input format, distinguishing it from sibling tools like json_format (formatting) and validate_json (validation). The scope is specific and immediately understandable.

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 provides explicit use cases: 'Use when a config, a CI file, or a Kubernetes manifest needs to be in the other format.' This gives clear context for when to use the tool, but it doesn't mention alternatives or when not to use it, so it stops short of a 5.

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 readOnly/idempotent/destructive annotations, the description discloses that the signature is NOT verified and that the response explicitly says so. It also warns not to treat decoded values as proof, adding critical behavioral context about limitations and security implications.

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, front-loaded with the core function, and uses three sentences to cover what it does, the security caveat, and usage guidance. Every sentence adds value with no fluff.

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 simple parameter set, comprehensive annotations, and existence of an output schema, the description covers all necessary context: function, usage limitations, and security warning. It is complete for an agent to correctly select and invoke the 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 schema covers 100% of parameters with a single 'token' parameter described as 'The JWT string,' which is self-explanatory. The description does not add extra parameter semantics, but the schema already fully documents it, so 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 the tool decodes the header and payload of a JWT and reports issued-at/expiry timestamps plus seconds remaining. This specific verb+resource pair distinguishes it from all sibling tools, none of which handle JWT decoding.

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 explicitly states when to use the tool ('debugging a token you already hold') and warns against using it for verification, noting that verification requires the secret and belongs in your own service. This provides clear usage context and exclusions.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds value by specifying the output is a downloadable/embeddable PNG and providing the stateless URL pattern, beyond what annotations convey.

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 two sentences long, front-loads the core functionality, and includes a useful URL example. Every sentence earns its place with zero 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?

For a simple one-parameter tool with an output schema, the description covers everything needed: purpose, output format, and an alternative access method. No significant 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 the 'text' parameter well described as 'The text or URL to encode.' The description reinforces that any text works but does not add substantial new meaning beyond the schema, so 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 explicitly states the tool converts any text or URL into a QR code PNG, with a clear verb and resource. It distinguishes itself from sibling tools (e.g., diff_text, json_format) by its specific function and mentions the output format.

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 clearly implies when to use the tool (whenever a QR code is needed) and mentions the stateless URL form as an alternative delivery method. It does not explicitly name exclusions or alternatives, but context with siblings makes the usage obvious.

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 goes well beyond annotations by disclosing that processing is rule-based, no model sees input, and same values map to the same placeholders for restorability. These details add meaningful behavioral context beyond the readOnlyHint and idempotentHint 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?

Two compact sentences, front-loaded with the core action and return value, then adding a key behavioral guarantee. No filler or repetition of schema/annotations.

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 two-parameter tool with a rich output schema and strong annotations, the description fully covers the core function, privacy model, deterministic mapping, and restoration capability. It is complete for an agent to select and invoke 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?

Input schema covers both parameters with clear descriptions (text, optional 'only' subset), so baseline is 3. The description adds no extra parameter-level details, but it does list the entity types that will be redacted by default, which indirectly informs the 'only' filtering behavior.

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 uses a specific verb ('Strip') and enumerates the exact resource types (emails, phone numbers, ID numbers, API keys, etc.), making it clear what the tool does. It also explicitly differentiates from sibling tools like diff_text and json_format by focusing on redaction and returning a restoration mapping.

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 'before sending text on' establishes a clear use case, and 'Rule-based only — no model sees the input' provides important context about when this is preferable. It does not explicitly name alternative tools for exclusion, but the sibling list contains no other redaction tool, so distinction is inherent.

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 destructiveHint=false, so the description doesn't need to restate safety. It adds value by describing the output format (every match with position and capture groups, named groups included), which goes beyond the semantics of the operations and helps the agent anticipate the tool's behavior.

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 two compact sentences that front-load the core purpose and then provide a practical usage note. Every word earns its place; there is 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?

Given the tool's low complexity, full schema coverage, and existing annotations that declare read-only behavior, the description sufficiently covers the functional context. It explains what the tool does, what it returns, and when to use it, leaving no significant gaps for an agent invoking it.

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 schema provides complete descriptions for all three parameters (pattern, text, flags) with 100% coverage, so the baseline is 3. The description adds minimal parameter-specific meaning beyond mentioning 'sample text' and 'pattern', but it doesn't conflict with the schema or add significant new semantics.

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 runs a regular expression against sample text and returns matches with positions and capture groups, including named groups. This specific verb and resource distinguish it from all sibling tools, none of which involve regex testing.

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 explicitly advises using this tool 'before wiring a pattern into code' to avoid guessing about escaping through JSON and shell. This provides a clear when-to-use context and an implicit alternative (guessing), making the intended usage unambiguous.

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 provided, the description must disclose behavioral traits, but it only mentions 'full-page' and PNG output. It omits details such as rendering behavior, handling of dynamic content, timeout limits, error scenarios, or authentication requirements. The pricing remark is irrelevant to behavior and does not contribute to transparency.

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 brief (two sentences) but the second sentence containing the pricing comparison is irrelevant to tool functionality and adds noise. The core idea is clear, but the extraneous marketing line prevents a higher score.

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 simple nature of the tool belt (no output schema, minimal annotations), the description should at least explain parameter usage and any limitations. It does not mention width semantics, error handling, or security considerations innately relevant to taking screenshots. The description is too minimal for a complete understanding.

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% and the description directly explains none of the parameters. The `url` parameter is self-evident from context, but `width` is completely unexplained. The description fails to provide any additional meaning beyond what the schema already implies, forcing the agent to guess its purpose.

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 function: capturing a full-page screenshot of any URL and producing a PNG. It is specific and unambiguous, and distinguishes itself from sibling tools (none of which are screenshot-related) by using a direct verb and resource.

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 does not provide explicit guidance on when to use this tool versus alternatives; it only includes a marketing comparison to paid APIs. There are no direct usage instructions, prerequisites, or context about typical use cases, so the agent is left without clear 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?

No annotations are provided, so the description carries the full burden. It mentions that it returns a .sql file with comments, but it doesn't disclose edge cases, limitations (e.g., complexity of queries, dialect support), or what happens if the request is ambiguous or the schema is incomplete.

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 one concise sentence that front-loads the purpose and output. It's efficient with 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?

Given the tool's complexity (SQL generation) and the lack of annotations and output schema, the description is somewhat minimal. It doesn't explain how the dialect parameter works, what inputs are expected (e.g., schema format), or any limitations. For a tool with this complexity, more detail would be beneficial.

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 schema has 3 parameters (schema, dialect, request) but 0% description coverage. The description mentions 'table schema' and 'plain-language request', which loosely maps to 'schema' and 'request', but it doesn't explain the 'dialect' parameter or what values it accepts. The description adds minimal value over 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 takes a plain-language request and table schema to produce a ready-to-run .sql file with comments. It distinguishes from siblings like transpile_sql (which converts between SQL dialects) and regex_test, but it doesn't explicitly name alternatives.

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 use case of generating SQL from natural language and schema, but it doesn't provide explicit when-to-use or when-not-to-use guidance or mention alternatives like transpile_sql for converting SQL. The distinction from siblings is minimal.

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?

No annotations are provided, so the description carries the full burden. It states the function (conversion/current time) and parameter formats but does not disclose behavioral traits such as output format, error handling for invalid zones, or whether it requires network access. For a pure utility, this is minimally acceptable but could be more explicit.

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 two sentences, front-loaded with the core action, and every word contributes value. It efficiently packs purpose, parameter semantics, and default behavior without 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?

The tool is simple and has no output schema or annotations. The description covers purpose and parameter basics, but it leaves ambiguity about what happens when 'from' or 'to' are omitted (e.g., if only 'to' is given, does it assume current time?). It also does not mention what the output looks like (e.g., formatted time string). For a simple tool, this is adequate but not fully 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?

Schema coverage is 0%; all three parameters are bare strings. The description adds critical meaning by specifying that 'from' and 'to' are IANA timezone identifiers (with example 'Asia/Shanghai') and that 'time' follows YYYY-MM-DDTHH:mm format with a default of 'now'. This significantly compensates for the schema's lack of details, though it does not clarify interactions among parameters.

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 converts time between time zones or gets current time in any zone, using a specific verb ('convert') and resource (time zones). It inherently distinguishes itself from siblings, which are unrelated to time utilities. The phrase 'from/to = IANA zone' adds intentional scoping.

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 usage by explaining what it does and gives examples of parameter formats, but it does not explicitly state when to use this tool over alternatives or exclude any scenarios. It provides enough context for a simple conversion tool, but lacks explicit when/when-not 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 declare readOnly/idempotent, but the description adds determinism ('same input always produces the same output') and exact error locations (line/column), going beyond structured metadata. This is valuable behavioral context.

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 sentences, each valuable: purpose, determinism, and use case. Front-loaded and no 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?

Description covers purpose, usage, determinism, and error behavior. Output schema covers return shape. For a conversion tool with rich annotations, it's 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?

Schema covers all parameters at 100%, so baseline is 3. The description adds a useful list of supported dialects for read/write, aiding parameter selection, though it doesn't add much beyond that.

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 a specific verb ('Convert') and resource ('a SQL statement from one dialect to another') and lists many supported dialects. It distinguishes itself from sibling formatting tools by focusing on SQL dialect conversion.

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 states when to use ('when migrating queries between databases or debugging dialect-specific syntax'). It doesn't mention exclusions or alternatives, but the sibling tools are unrelated, so the context is clear.

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?

No annotations are provided, so the description carries the burden, and it does a reasonable job by spelling out the invocation contract and giving concrete examples. It does not describe output formatting or invalid-unit behavior, but for a side-effect-free conversion tool this is not a critical omission.

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 a single front-loaded sentence followed by an example, with no filler or redundant restating of the title. Every phrase adds either scope or usage detail.

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 three-parameter converter with no output schema, the description is reasonably complete: it communicates scope, parameter order, and examples. It could be improved by listing accepted unit aliases or edge-case behavior, but the tool is simple enough that an agent can construct a valid call.

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 0%, so the description must compensate; it does by defining roles through the pattern 'value + from + to' and examples like '100 km mi, 25 c f'. This makes value, from, and to understandable despite the schema providing only raw 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 immediately states 'Convert units' and enumerates specific categories (length, weight, temperature, area, volume, speed, data size), giving a precise verb+resource scope. This also differentiates it from sibling timezone_convert by explicitly covering non-timezone unit types.

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 makes it clear this should be used for unit conversions and shows the required input pattern 'value + from + to'. It does not explicitly mention alternatives or exclusions, but the domain is unambiguous and the sibling list reinforces that timezone conversions belong to a different tool.

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 and idempotentHint. The description adds valuable behavioral context including 'Returns the specific violations, not just true/false' and clarifies the check is limited to 'required + types only', not full JSON Schema. This goes beyond the 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?

Every sentence in the description earns its place: what it does, what it returns, its limitations, and when to use it. The structure is front-loaded with the core purpose and remains tight without redundant details.

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 tool is simple with two parameters and an output schema exists. The description covers purpose, usage, limitations, and return behavior comprehensively. There is no need to explain return values given the output schema, and the description sufficiently covers all relevant context.

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 already provides 100% coverage with descriptions for both parameters. The description reinforces meaning by explaining the 'schema' parameter checks 'required[] and properties[].type', which adds context beyond the schema text. Baseline is 3, and this extra context warrants a 4.

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 validates JSON text and optionally checks required keys and types. It uses specific verbs ('Checks', 'Returns') and distinguishes itself from siblings like json_format by focusing on validation rather than formatting.

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 provides a concrete use case: 'Use before feeding generated JSON into something that will fail on it.' It also excludes full JSON Schema validation, but does not explicitly name alternative tools. Still, the guidance is clear and actionable.

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?

Although annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, the description adds valuable non-obvious behavioral context: 'Deterministic and free: it calls no model, costs nothing, and never runs out of quota.' This informs the agent about cost, reliability, and independence from model quotas, going beyond what annotations provide.

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 three sentences, each adding distinct value: the core function, the multi-step recipe capability, and operational characteristics (free/deterministic). It is front-loaded with the most critical information and contains no redundancy or fluff.

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 tool is simple with one parameter, has annotations covering safety, and an output schema. The description provides complete context: what it does, when to use it, additional output capabilities, and cost/reliability characteristics. Nothing essential 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?

The schema covers 100% of the single parameter with a clear description and examples, so the baseline is 3. The description goes further by emphasizing 'plain language (any language)', which clarifies that the parameter accepts natural language across languages, adding semantics not fully captured 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 states exactly what the tool does: 'Describe a task in plain language... and get back exactly which tools on this server do it, with ready-to-run example calls.' This clearly distinguishes it from the sibling utility tools, which perform specific operations rather than tool discovery.

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 explicitly says 'Call this FIRST when you are not sure what this server offers', providing clear context for when to use. It also contrasts with the alternative of 'reading the whole catalogue and guessing'. However, it does not explicitly state whhen not to use it (e.g., when you already know the exact tool), so it lacks explicit exclusions.

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