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

With no annotations provided, the description carries full responsibility. It explicitly states 'Deterministic string matching — no API key and no model call required,' which transparently explains the method and resource needs. This exceeds the minimum but could mention side effects (e.g., read-only, exit codes).

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 concise sentences with no redundant wording. The first sentence states the core purpose, and the second clarifies the technical approach. Ideal for quick agent comprehension.

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 (3 params, no output schema) and the description is enough for an agent to understand its role and behavior. It does not specify return format or error handling, but for a checking tool with no output schema, this is not critical. The mention of deterministic matching covers the execution 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 schema covers all three parameters and the descriptions add useful context (e.g., 'Path to locale tree, .arb directory, or .xcstrings file' for path, 'Source language code' for source, 'Path to a glossary JSON file' for glossaryPath). Since coverage is 100% and descriptions are meaningful, this scores above baseline.

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 ('enforce') and identifies the resource (glossary compliance) across a locale tree. It clearly differentiates from sibling tools like check_locales or check_placeholders, which focus on different aspects of localization.

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 the tool is for checking glossary terms but does not explicitly state when to prefer it over alternatives or list exclusion criteria. It could benefit from a note like 'Use when you need to validate glossary adherence rather than general locale structure.'

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 enumerates the checks performed (missing/orphaned keys, dropped/invented placeholders, collapsed plurals, empty values, untranslated copy) and states determinism, but does not specify the output format, return codes, or behavior on success/failure. Users know what it does but not exactly what they will receive.

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, well-structured sentence that lists the validation checks in a clear sequence. It is concise without unnecessary detail, providing essential information in a compact form.

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 gives sufficient context about the tool's function within the set of sibling tools (e.g., validation vs. diffing or reviewing), but it omits an output schema and details about error handling or return structure. Without these, users may need additional information to fully integrate 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?

All four parameters are described clearly in the schema: path indicates the locale tree/directory/file, source specifies the language code, ignoreKeys explains the glob pattern for silencing, and glossaryPath points to a JSON glossary. The descriptions fully cover the parameters with no 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's purpose: validating translated locale files against a source language, listing specific validation checks (missing keys, placeholders, plurals, empty values, untranslated copy). It also notes that the tool is deterministic and requires no API key or model call, reinforcing its intended use.

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 listing what it validates and noting it requires no API key or model call, which suggests it can be run offline. However, it does not explicitly state when to prefer this tool over siblings like diff_locales or review_locales, or what conditions trigger its use.

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 carries the full burden. It correctly indicates a verification action (implying read-only), but does not disclose return format, error behavior, or placeholder syntax expectations.

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, focused sentence with no redundant words. It conveys the essential function and a notable characteristic ('no LLM call') efficiently.

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 verification tool, the description is mostly complete. It lacks an output schema and specifics about placeholder format, but the inputs are simple and the purpose is clear enough for an agent to use 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 descriptions are minimal ('The source string', 'The translated string to check'), but the tool description clarifies that placeholders are the focus, giving meaningful context to both parameters. Coverage is complete.

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: verifying that a translated string preserves all placeholders from the source. The verb 'Verify' and specific object make the action unambiguous, and it is distinct from sibling tools.

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 through '(no LLM call)' suggesting a lightweight deterministic check, but it does not explicitly state when to prefer this over siblings or provide exclusions. The context 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 must convey behavior. It discloses the output type (missing and obsolete keys per language) and notes that no API key is required, but it does not state whether the operation is read-only, whether it modifies anything, or how errors are handled. This is partial 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 concise and well-structured. It front-loads the key question ('what needs translating?') and then specifies the two output categories, followed by a short authentication note. Every sentence adds value with no redundant 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 tool's simplicity and lack of an output schema, the description provides sufficient context: it explains the output conceptually (per-language missing and obsolete keys) and mentions authentication. It does not specify the return format or edge cases, but for a diff tool this is adequate, though not exhaustive.

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 descriptions for all three parameters. 'path' and 'source' are well-defined, but 'lang' is vague ('Limit to one language') – it does not specify if this is a target language code, a filter, or its relationship to 'source'. Overall, the descriptions add meaning beyond parameter names, but the ambiguity of 'lang' prevents a top score.

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: to answer 'what needs translating?' by listing missing keys and obsolete keys per language. This is specific and distinguishes it from general locale tools, though it doesn't explicitly name siblings. The core function is unambiguous.

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 is given on when to use this tool versus alternatives like check_locales or review_locales. The description implies use for identifying translation gaps, but it does not state conditions, exclusions, or comparisons to sibling tools, leaving the agent to infer applicability.

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 mentions that BCP-47 codes work and that some have friendly names, which gives a hint of behavior but doesn't disclose return format or any other constraints. For a simple list tool this is adequate but not rich.

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?

A single sentence that is front-loaded with the purpose and includes a clarifying note about BCP-47. 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 zero-parameter listing tool, the description is complete: it states what is returned and the scope. No output schema exists, but the description covers what an agent needs to know to call 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 tool has zero parameters, so the schema is empty. The description adds meaning by explaining that it returns recognized codes and friendly names, which compensates for the lack of parameters. Baseline for 0 params is 4, and the description maintains 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?

The description clearly states the tool lists language codes and names that Shipi18n recognizes, with a specific verb and resource. It distinguishes itself from sibling tools (check, diff, review, translate) by being a listing operation.

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 context on when to use it: to get recognized language codes and friendly names, and notes that any BCP-47 code works. It doesn't explicitly exclude alternatives, but for a list tool the usage is self-evident among the siblings.

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 carries the behavioral burden and does well by disclosing that the server makes no model call, needs no API key, and excludes structurally broken keys. It also states what is returned—source/translation pairs plus review criteria—giving agents the essential behavioral context without requiring them to infer 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 three tight sentences, each earning its place: it states the purpose and output, discloses the no-model-call/no-API-key behavior, and routes broken-key work to check_locales. It is front-loaded and contains no 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 retrieval tool with no output schema and no annotations, the description explains what the response contains, the key behavioral constraints, and the boundary with check_locales. It leaves the exact content of 'review criteria' unspecified, but the stated purpose gives an agent enough context to call the tool 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. The description does not add parameter-specific meaning beyond what the schema already documents for path, lang, limit, and source, but that is acceptable because the schema fully covers all 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 uses a specific verb and resource: 'Return source/translation pairs plus review criteria,' and clearly states the tool's purpose—enabling semantic review of translation quality. It also differentiates from the sibling check_locales by noting that structurally broken keys are excluded.

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: when an agent needs to judge translation quality using its own reasoning, with no model call or API key. It also explicitly routes structurally broken key checks to check_locales, though it does not discuss when to prefer other siblings like check_glossary or diff_locales.

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 explains the core behavior of reading, translating, and writing, and implies overwriting by mentioning incremental mode. However, it does not mention error handling, provider selection, or output details beyond file names.

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, with two sentences, and effectively communicates the main function without unnecessary 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?

The description lacks context about how it relates to sibling tools like translate_json, and does not specify the provider/model usage or potential side effects, making it incomplete for full 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?

Most parameters have descriptions (5 out of 7), but 'model' and 'provider' lack descriptions. The provider has an enum, but model is completely unspecified, 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 reads a JSON locale file, translates it, and writes output files, which is specific and distinct from potential sibling tools like translate_json.

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 gives a tip about using incremental=true but does not explicitly state when to choose this tool over siblings like translate_json, so guidance 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?

Without annotations, the description provides some behavioral insight (preserving structure/placeholders, using external LLM keys, legacy mode) but does not explicitly state whether the operation is read-only or has side effects. It implies a translation action but lacks a clear safety profile.

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 providing useful information: core functionality, key requirement, and legacy behavior. It is fairly concise but the legacy note adds a slight layer of complexity that could be separated or clarified.

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 gives context about the tool's purpose, prerequisites, and alternatives. It does not describe output format or error scenarios, but for a translation tool these are not essential for basic usage and the schema covers parameter specifics.

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 already provides 100% coverage with descriptions for all five parameters, so the description adds little beyond what is already known. It mentions 'target languages' and 'source locale' but doesn't elaborate on each parameter's meaning or constraints beyond 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 function: translating an i18n locale JSON object to one or more target languages while preserving structure and placeholders. It also distinguishes itself from validation tools and mentions legacy behavior, giving a full picture of its purpose.

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 states the requirement for an LLM key, directs users to validation tools for key-free work, and mentions legacy mode. This gives clear guidance on when to use this tool versus alternatives.

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