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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description carries a lighter burden. It adds one useful behavioral detail: the tool handles input already in any of these styles. However, it does not describe edge-case behavior like handling of non-alphanumeric characters or the exact slug format.

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 with the core action and supported styles front-loaded, and no filler. The long style list is necessary because it directly matches the required enum values.

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, read-only, idempotent converter with only two parameters and an output schema, the description covers the essential usage and input compatibility. The only noticeable gap is that 'slug' is not precisely defined, leaving a minor ambiguity about its exact normalization behavior.

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%: 'text' is described as the text to convert and 'style' is an enum listing all target conventions. The description largely restates what the schema already provides rather than adding deeper parameter semantics, so it stays at the 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 opens with a specific verb and object: 'Rewrite text into a naming convention', and enumerates every supported style. This makes the tool's purpose unmistakable and clearly distinguishes it from the sibling text-analysis 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 purpose and supported transformations make it clear when this tool should be used: whenever text needs to be converted into one of the listed naming conventions. It does not explicitly name alternatives or exclusions, but the sibling tools serve unrelated functions, so the usage context is 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral detail by specifying the output format ('unified diff'), the line-by-line granularity, and the special case of returning a note when inputs are identical. No contradiction with 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?

The description is compact and front-loaded: it names the operation, the output format, and the special identical-input case in two sentences. Every sentence adds value, with 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?

For a simple read-only diff tool with an output schema and comprehensive annotations, the description is complete. It covers the core behavior, the use case, and the edge case of identical inputs. Nothing essential is missing for an agent to decide when and how to invoke 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?

Schema description coverage is 100%, so the parameters (before, after, context_lines) are already fully documented in the schema. The description adds high-level intent but does not introduce new parameter-level detail 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 states a specific action and resource: 'Return a unified diff between two versions of a text, line by line.' It also clarifies the intended use case (comparing draft and revision) and notes the identical-input behavior. This clearly distinguishes the tool from siblings like summarize_text or text_stats.

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 clear context for when to use the tool: 'so edits between a draft and a revision can be reviewed precisely.' It does not explicitly name alternatives or exclusions, but the sibling tools are functionally distinct enough that the intended usage is evident.

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 and idempotent annotations, the description adds meaningful behavioral details: results are de-duplicated and returned in the order they first appear. This helps an agent understand output characteristics without needing to invoke the tool.

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 concise sentences front-load the core purpose and follow with the key behavioral detail. Every word earns its place; there is no redundant or filler content.

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 single simple parameter, full schema coverage, an output schema, and read-only/idempotent annotations, the description is complete. It states the input, the entity categories, deduplication, and ordering, leaving no critical gap.

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 already described as 'The text to scan.' The description adds no parameter-specific meaning beyond what the schema provides, so the baseline score of 3 applies.

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 ('Pull structured items out of free text') and enumerates the exact entity types (email addresses, URLs, #hashtags, @mentions, phone numbers, standalone numbers). This clearly distinguishes the tool from siblings like extract_keywords, since the output categories are explicit and structured.

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 clear context for when to use the tool: whenever structured entities need to be pulled from free text. It does not explicitly name alternatives or exclusions, but the enumerated entity types make the applicable use case 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?

Beyond the readOnly/idempotent annotations, the description discloses meaningful behavior: stopwords and very short tokens are filtered out, and the output includes counts and relative frequency. This adds useful behavioral context without contradicting 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?

The description uses three efficient sentences, front-loading the core behavior first and following with purpose-driven use cases. Every sentence adds value and there is no redundant restatement of the tool name or title.

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, read-only extraction tool, the description is complete: it explains the output, filtering behavior, and practical applications. The presence of an output schema and full parameter coverage means no essential calling 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 description coverage is 100%, so the schema fully documents all three parameters. The description adds context about 'meaningful words' and stopword filtering, but does not meaningfully deepen parameter-level semantics beyond what the schema already provides, so the baseline of 3 applies.

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 operation: 'Return the most frequent meaningful words in the text, with counts and relative frequency.' This clearly identifies the resource (text), the output (keywords with frequency), and naturally distinguishes it from siblings like extract_entities or summarize_text.

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 concrete use cases: 'tagging, SEO checks or spotting what a document is actually about.' However, it does not explicitly mention when not to use this tool or name alternatives, though the use-case guidance is clear enough for an agent to select it appropriately.

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 cover safety (readOnlyHint, idempotentHint, destructiveHint). The description adds behavioral context by noting that it produces both numeric scores and a plain-language interpretation, which informs the agent about the nature of the output beyond the structured 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 sentences, no fluff, and the core computation is front-loaded before the usage guidance. Every phrase 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?

For a simple one-parameter, read-only tool with a full output schema and rich annotations, the description fully equips an agent to invoke it correctly. It states what is computed, what kind of output is generated, and the intended use case.

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 fully documents the single 'text' parameter as 'The text to score' (100% coverage), so the description does not need to add much. It confirms the purpose of the text but adds no format, length, or language constraints.

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 ('Compute') and resource ('Flesch Reading Ease and Flesch-Kincaid grade level'), naming concrete outputs that distinguish it from siblings like text_stats or summarize_text. The title 'Score readability' is also reinforced, not merely restated.

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 clear context: 'Use it to check whether a draft matches its intended audience before publishing.' This tells the agent when to apply the tool, though it does not explicitly name alternatives or state when not to use it.

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 beyond the readOnly/idempotent annotations by explaining the exact scoring mechanism, output ordering, and offline behavior. It accurately describes what the tool does and aligns with the annotations, with no 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?

Two sentences deliver the essential information with zero waste: what the tool produces, how it works, and a key operational characteristic. Every clause contributes to understanding.

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, an output schema, and strong annotations, the description is fully sufficient. It explains the algorithm, output ordering, and offline nature, leaving no critical gaps for an agent 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?

The input schema already provides 100% parameter coverage with clear descriptions, defaults, and constraints for both 'text' and 'max_sentences'. The description does not add new parameter-level meaning but also does not need to, so the baseline of 3 applies.

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 ('Produce an extractive summary') and explains the exact method. It is clearly distinct from sibling tools like text_stats, extract_keywords, and readability, which target 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 gives clear context: it is for extractive summarization and works offline without a model call. It does not explicitly name alternatives or state when not to use the tool, but the context is strong enough for an agent to infer appropriate 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?

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds value by disclosing the analytical scope, including derived metrics like average lengths and estimated reading time, which are not implied by the annotations alone. There is no 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?

Two sentences carry all essential information: what is computed and when to use it. The metric list is front-loaded and every clause earns its place with 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?

With one simple parameter, a full output schema, and strong annotations, the description is complete for an agent to invoke the tool correctly. It covers purpose, use cases, and behavioral scope without needing to explain return values.

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 the parameter description 'The text to analyze' is already clear. The tool description adds no new parameter-level semantics, such as formatting constraints or edge-case behavior, so the baseline 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 uses a specific verb ('Count') and names the exact resource ('a piece of text') plus a rich list of concrete metrics: characters, words, unique words, sentences, paragraphs, lines, and reading time. This clearly distinguishes it from siblings like summarize_text, extract_keywords, or convert_case.

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 clear use cases: 'check length limits or profile a draft before editing.' It does not explicitly name sibling alternatives or state when not to use it, but the context is strong enough for an agent to select it appropriately.

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