Moltline Research Desk

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

Annotations already declare readOnlyHint and idempotentHint, and the description reinforces these with 'Every call is read-only and idempotent.' More importantly, it discloses a critical behavioral trait beyond annotations: on invalid input, the tool returns an error object instead of raising a protocol error, with an example error message. This adds significant 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 about 10 lines, front-loaded with the core purpose, followed by a JSON example, then usage guidelines, and finally error behavior. Every sentence provides essential information, with no fluff 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?

Given the tool's simplicity (4 parameters, all with schema descriptions, output schema present), the description covers all necessary aspects: purpose, example, when-to-use, when-not-to-use, assumptions (normal approximation), error handling, and safety guarantees. It is fully 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?

Schema description coverage is 100%, so baseline is 3. The description provides a concrete example mapping parameters to the output, and mentions the valid confidence levels (90/95/99) and constraints (n>=2, std_dev>=0) that are already in the schema but reinforced. The example and error formatting add practical context 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 explicitly states 'Compute a confidence interval for a mean (normal approximation)' and provides a concrete input/output example. It distinguishes itself from proportion and two-group tools by referencing the sibling ab_test, making the purpose 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?

The description advises 'Use on data already collected, for a mean' and warns 'Not for proportions or two-group comparisons - the data server's ab_test compares two proportions.' It also alerts about unreliability on small or skewed samples, providing clear when-to-use and when-not-to-use guidance with an explicit alternative.

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 states 'Every call is read-only and idempotent, so after correcting the input it is always safe to retry', which adds behavioral context beyond the annotations (readOnlyHint, idempotentHint, destructiveHint). It also transparently describes error handling: 'never raises a protocol error — it returns {"error": ...}'.

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 plus a succinct example. The description is front-loaded with the core action, then provides usage guidance, error behavior, and safety. Every sentence adds value 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?

Given the output schema exists and annotations are present, the description covers all necessary context: purpose, when to use, error handling, safety guarantees, and a concrete example. It is complete for an agent to understand and invoke 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 description coverage is 100%, so the baseline is 3. The description provides a typical input example that illustrates parameter usage, but does not add new meaning beyond what the schema already describes. The example reinforces the schema but does not introduce 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 starts with 'Format a citation in APA 7, MLA 9, or Chicago author-date style', which clearly states the specific verb (format) and resource (citation) with style variants. The sibling tools are all statistical or product-related, so this tool is well-distinguished.

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 says 'Use when the source details are already known and only the formatting is missing. Not for finding or verifying a source.' This provides clear when-to-use and when-not-to-use guidance, directly aiding an agent in selecting this tool over alternatives.

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

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

Annotations already mark the tool as read-only (readOnlyHint=true) and idempotent (idempotentHint=true). The description reinforces these traits ('Every call is read-only and idempotent') and adds critical behavioral details not in annotations: error handling ('never raises a protocol error — returns an error object with fix guidance'), result cardinality ('returns exactly one skill'), and plan requirement ('no plan required'). No contradictions 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 is well-structured with the core purpose in the first sentence, then typical I/O, usage guidance, error handling, and idempotency note. It is front-loaded and every sentence adds value. While it could be slightly trimmed (e.g., 'FREE' is redundant with 'no plan required'), it remains efficient and highly readable. A minor deduction for slight 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?

Given the tool has a single parameter fully described in schema, an output schema (not shown but present), and annotations covering behavioral hints, the description covers all essential aspects: purpose, input (slug with example), output shape (slug, skill, instructions), error behavior, usage guidelines, and idempotency. No notable 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% – the slug parameter is well-described in the schema as 'Product slug exactly as returned by list_products'. The description adds value beyond the schema: it shows a typical input/output example ('thesis-advisor' → skill and instructions), explains the source of valid slugs (list_products), and describes error behavior for invalid slugs. This extra context justifies a score above the baseline of 3.

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 loads a product's free gateway skill with complete instructions, using the verb 'load' and specifying the resource. It differentiates from the sibling get_full_skill by noting this is the free skill with no plan required, and provides a typical input/output example ('thesis-advisor') that clarifies the exact purpose. The scope is specific and 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?

Explicitly states when to use ('when the caller wants usable instructions immediately') and when not to use ('not for the product's other skills'), naming the alternative get_full_skill and the prerequisite of a paid plan. Also notes idempotency and safe retry, giving clear context for invocation.

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, idempotentHint, destructiveHint, but the description adds crucial context: it never raises a protocol error, instead returning an error object with fix instructions. It also confirms the call is read-only and idempotent, matching annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, includes a typical input/output example, provides usage guidelines, summarizes behavior, and states error handling—all in a compact, well-organized format. Every sentence adds value; 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?

Given the tool's simplicity (single parameter, full schema coverage, rich annotations, existing output schema), the description covers all essential aspects: purpose, usage context, error behavior, and idempotency. It leaves no significant gaps for an agent to correctly select and invoke this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (slug is described). The description adds value beyond the schema by giving a concrete example ('thesis-advisor') and referencing list_products as the source for valid slugs. This aids correct invocation, justifying a score slightly above the baseline of 3.

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 'Load one product in full: its persona plus every paid skill' and later repeats 'Returns persona plus every skill for one product.' It clearly identifies the verb (load/return) and resource (full product), and distinguishes from siblings like get_full_skill and get_free_skill/list_products.

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 when-to-use guidance: 'Use when the caller wants the whole product.' It also tells when not to use it: 'Not for a single skill (get_full_skill) and not for a free look, which list_products and get_free_skill provide with no plan.' Additionally, it mentions the PREMIUM license requirement.

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 provide readOnlyHint and idempotentHint. The description adds valuable behavioral context: it never raises protocol errors, returns error objects with fix instructions, and is safe to retry. This goes beyond annotations and helps the agent understand error handling and idempotency. 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 is front-loaded with the main purpose and includes several pieces of information (example, usage guidance, error handling, safety). It is moderately concise; each sentence adds value. Minor redundancy could be trimmed, but overall it is well-structured.

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 has 2 parameters, no enums, and an output schema, the description is fairly complete. It explains the output shape (slug, skill, instructions) and error handling. It mentions licensing and distinguishes from siblings. It could mention authentication briefly, but it still provides sufficient context for correct 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 coverage is 100%, so the baseline is 3. The description provides a typical input example and explains the output shape, but it does not add new semantic information about the parameters beyond what the schema descriptions already provide. The example is helpful but not sufficient to raise the 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 loads one paid skill's complete instructions from a product. It specifies the verb 'Load' and the resource 'one paid skill's complete instructions'. It also distinguishes from sibling tools by explicitly naming get_free_skill and get_full_product, making the purpose specific and 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?

The description provides explicit guidance: 'Use when the caller wants one specific paid skill.' It also states when not to use it: 'Not for the free gateway skill, which get_free_skill returns with no plan, and not for every skill at once (get_full_product).' This clearly differentiates usage from 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral context beyond these: it explains that the tool never raises a protocol error but returns an error object, and that after correcting input it is always safe to retry. This provides error-handling and retry safety details that annotations do not cover.

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 serves a purpose: announcing the product line, confirming no arguments, detailing the return structure, explaining usage, and describing error behavior. The information is front-loaded and logically organized. There is 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?

Given the tool's simplicity (zero parameters, no required inputs, and an output schema not shown but referenced), the description covers all relevant aspects: purpose, parameters, output structure, usage guidance, error handling, and comparisons with sibling tools. It is fully self-contained and leaves no gaps.

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 zero parameters, so the description's statement 'Takes no arguments' confirms the schema. The baseline for 0 params is 4. The description also adds context about the return structure, which indirectly helps the agent understand the tool's output, though it does not add parameter-specific semantics. Still, it is clear and sufficient.

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 and resource: 'List every product in the Research Desk line with its included skills.' It also distinguishes itself from sibling tools like get_free_skill, get_full_product, and get_full_skill by explaining that it returns metadata only, not instructions or persona text. This is a clear and differentiated 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?

The description explicitly tells when to use the tool: 'Use when the caller wants to see what this server covers.' It also provides clear exclusions: 'Not for keyword search...which the catalog server's search_catalog does, and not for instructions the caller can act on (get_free_skill).' Moreover, it directs the user to use the returned slug values with get_free_skill, get_full_product, or get_full_skill, providing explicit alternatives.

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

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

Beyond annotations (readOnlyHint, idempotentHint), the description adds critical behavioral details: it uses maximum variance with finite-population correction, and crucially states that invalid input never raises a protocol error but returns an error object with fix instructions. This disclosure is valuable for an AI agent.

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 well-structured with front-loaded purpose, followed by algorithmic detail, usage guidance, and error behavior. Every sentence adds value; there is no fluff. The 'FREE' note is minor but not detrimental.

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 moderate complexity, the description covers all essential aspects: purpose, mathematical assumptions, input/output examples, error handling, and safety (read-only, idempotent). With an output schema available, the return format is already addressed, making this description self-sufficient.

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?

Although the input schema has 100% description coverage (baseline 3), the description adds meaningful context: it explains the p=0.5 assumption and finite-population correction when population is given, which are not evident from the schema alone. The typical input example further clarifies parameter interplay.

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 calculates survey sample size for a given confidence level and margin. It explicitly differentiates from sibling tools stats_describe and confidence_interval by stating it is used before data collection, not for analyzing already collected data.

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 usage guidance: 'Use before collecting data, to size a survey. Not for analyzing data already collected (stats_describe, confidence_interval).' It also gives error recovery instructions, saying it is always safe to retry after correcting input, which aids tool invocation decisions.

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 adds valuable behavioral detail beyond annotations: it states the tool is 'FREE', 'read-only and idempotent', and explains that errors are returned as object with a fix message ('never raises a protocol error'). It also provides an example output. This is transparent and consistent 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 is well-structured and front-loaded: a one-sentence summary, then example, then usage guidelines, then error handling. Every sentence is meaningful and earns its place. Despite reasonable length, it is concise and easy 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?

Given the simple tool (one parameter, schema coverage 100%, annotations, output schema present), the description is complete. It explains output, errors, usage context, and safety. No missing information critical for an agent to correctly 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 input schema already covers the parameter 'numbers' with full description (type, minItems). The description adds an example input but does not introduce new semantic meaning beyond the schema. Baseline 3 is appropriate given schema coverage is 100%.

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: 'Describe a numeric dataset: center, spread, quartiles, and outliers.' It uses a specific verb-resource combination and distinguishes from siblings by explicitly noting what it is not for (interval estimates, sample size).

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 'Use as a first summary of one numeric dataset' and contrasts with sibling tools 'confidence_interval' and 'sample_size'. It also explains error handling and retry safety, providing clear when-to-use and when-not-to-use guidance.

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