Game Dev Outsourcing Directory

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

Annotations already indicate read-only and idempotent behavior, but the description goes further by disclosing the return format ('hourly, monthly and whole-project ranges'), the inclusion of assumptions, and the editorial nature of the data (not real quotes). This is valuable context beyond the structured annotations and directly informs the agent how to interpret and present the results.

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 concise sentences that are front-loaded with the tool's core function, followed by return details and usage guidance. Every sentence adds necessary information without redundancy. The structure is highly efficient for an agent to parse and act on.

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 (4 parameters, nested roles array) and the presence of an output schema, the description provides sufficient context for selection and invocation. It covers what the tool does, what inputs are needed, what outputs to expect, and the proper use of the results. With schema and annotations handling structured detail, the description is 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?

The input schema covers all parameters in detail (roles, weeks, region, hoursPerWeek) with clear descriptions, so the baseline is 3. The description adds minimal semantic value by referring to 'roles (discipline, seniority, headcount)' and 'optional duration in weeks' which simply maps to existing schema descriptions. It does not introduce any new parameter meaning beyond what the schema already provides.

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 the specific verb 'estimate' and identifies the exact resource: 'what an outsourced game team costs in USD'. It also enumerates the input types (roles, region, duration) and clearly differentiates from sibling tools like get_studio or search_studios. The phrase 'Use for "what would X cost" and budgeting questions' reinforces the tool's unique 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 gives clear context for when to use the tool: 'what would X cost' and budgeting questions. It also provides a crucial usage caution: 'These are this site's editorial market ranges... not quotes from any listed studio — present them as a budget range, never as a price.' This is strong guidance, though it does not explicitly mention alternatives or when not to use other tools.

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 read-only and non-destructive behavior. The description adds value by stating it retrieves 'full text' and is intended 'for quoting and citation,' which is useful context beyond the annotations. 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?

Two concise sentences, front-loaded with the core action and purpose. Every phrase earns its place: id format and prerequisite are stated 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?

The tool is simple (one parameter), has a rich schema, output schema, and helpful annotations. The description fully covers what, why, and the prerequisite (search first), so it is complete for this complexity level.

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%, but the description still enriches the parameter meaning by showing id format examples ('company/<slug>', etc.) and reinforcing that the id comes from a search result. This goes beyond the schema's basic description.

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 verb ('Retrieve'), the resource ('directory document'), and the specific purpose ('for quoting and citation'). It also explains the id format and explicitly ties the tool to search results, distinguishing it from sibling getter tools that are type-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 gives explicit usage context: 'Always call search first to get an id.' This tells the agent when to use this tool. However, it does not explicitly mention alternatives (e.g., get_answer, get_ranking) or when not to use it, so it falls 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that it returns full question-and-answer text and links to related pages, giving useful behavioral context without contradicting 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 two sentences, front-loaded with the core purpose, and includes usage guidance without unnecessary detail. Every sentence 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 retrieval tool with strong annotations, the description is complete: it states the return content (full Q&A text with links), the source (list_answers), and the intended use cases. No critical information 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 coverage is 100% for the single 'slug' parameter, which already provides an example. The description clarifies that the slug comes from list_answers, but this is largely redundant with the schema, so no significant added meaning beyond 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 clearly states the tool 'Return the full question-and-answer text of one buyer guide by its slug from list_answers, with links to related pages.' The verb and resource are specific, and the reference to list_answers differentiates it 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 explicitly says 'Use for advice questions' and lists concrete topics (vetting a studio, pricing models, paid tests, etc.), while advising against answering from memory. It does not name alternative tools but contrasts with memory, providing clear context.

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 (readOnly, idempotent, non-destructive). The description adds valuable behavioral context: figures are recomputed from the live database and move over time, which warns the agent that values may change and should be quoted as authoritative.

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 core purpose, followed by usage guidance. No wasted words; every clause adds value.

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 no parameters, full output schema, and annotations covering safety, the description provides the necessary context: purpose, usage, and the live/recomputed nature. It is complete for a simple query 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 tool has zero parameters, so baseline is 4. The description explains what the tool does but doesn't need to describe parameters that don't exist. It adds meaning by listing the breakdown dimensions, which is helpful context.

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 returns directory totals and breakdowns by multiple dimensions (country, region, service, engine, platform, team size). This is specific and distinguishes it from sibling tools like get_ranking or search_studios.

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 this tool ('how many studios...' or 'which country has the most...') and provides guidance to quote these figures instead of counting search results, explaining that the counts move. This clearly differentiates it from 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 the annotations (readOnly, idempotent, non-destructive), the description discloses that payment cannot influence positions, the order comes from a stored score tracking listing completeness, and that it ranks documentation rather than studios. This is significant behavioral context not present in 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 concise and well-structured: purpose in the first sentence, ranking methodology and caveat in the second, and a pairing suggestion in the third. Every sentence adds valuable guidance without unnecessary 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 (one parameter, no output schema), the description fully covers what the agent needs to know: what the list ranks, how the order is determined, limitations, and relationship to sibling tools. Annotations handle safety, so no 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?

The schema already provides 100% coverage for the single parameter 'slug', including examples. The description repeats that the slug comes from list_rankings without adding new semantic information, so it meets the baseline but does not elevate it.

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 returns published positions in a ranked list, with a specific input (slug from list_rankings). It differentiates this from sibling tools by clarifying it ranks documentation completeness, not studios, and explicitly suggests pairing with search_studios.

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 (to get a ranking by slug) and when not to use (do not answer 'best studios' from this alone). It names an alternative (search_studios) and explains why, giving clear usage boundaries.

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 exactly what the return includes (fields) and what it does not include (contact details). This goes beyond the structured data and gives the agent useful 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?

The entire description is two sentences: the first states the core function and return contents, the second provides usage context and a caveat. Every clause earns its place, with no repetition or fluff. Front-loaded with the action and resource.

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 single-parameter read-only tool with no output schema, the description is fully adequate. It tells what is returned, when to use it, and what is missing. The sibling context (search_studios) completes the workflow picture. No additional information is needed for correct usage.

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, including a clear description of 'slug' and acceptance of full URLs. The description mentions 'by its slug' but adds no extra meaning beyond the schema. Since the schema already does the heavy lifting, a 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 uses a specific verb ('Return') with a clear resource ('one studio's full directory listing') and identifies the identifier ('by its slug'). It lists the exact fields returned, distinguishing it from siblings like search_studios which is for searching. The purpose is unambiguous and differentiated.

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 this tool: 'Use after search_studios when you need detail on one studio, or when the user names a studio whose gamedevoutsourcing.com slug you already have.' It also notes a limitation ('Contact details are not available here'), which helps set expectations and prevents misuse. This is clear, actionable 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, and non-destructive behavior, so the safety profile is covered. The description adds valuable context about the content scope (topics covered) and the output properties (slug, URL, summary), going beyond the annotations without contradicting them.

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: the first packs the tool's functionality and output into a clear, front-loaded list, and the second gives direct usage guidance. Every word earns its place, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with no parameters and an output schema (indicated by context), the description is fully complete. It explains what the tool lists, the type of content, the output fields, and how to use it in a workflow, leaving no significant gaps for an agent to resolve.

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 description cannot add parameter-level meaning. Per the baseline rule for 0 params, this scores a 4. The description does mention what the output contains, which helps frame the tool's usage even though parameters are absent.

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 lists editorial Q&A guides for buyers, with specific examples of topics and the output fields (slug, URL, summary). It clearly distinguishes this tool from siblings by naming get_answer as the follow-up tool, 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 provides explicit usage guidance: 'Use to find the right guide before calling get_answer.' This tells the agent when to use this tool and directly references an alternative, fulfilling the highest bar for this dimension.

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

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds crucial semantic context: the order measures how completely a listing is filled in, not studio quality, and is explicitly not an endorsement. This goes beyond annotations to explain how to interpret the returned data, enriching the tool's behavioral contract.

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 long, front-loaded with the core purpose and examples. Each sentence earns its place: the first defines the output, the second gives usage direction, and the third clarifies the order's meaning. No fluff or repetition exists.

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, read-only list endpoint, this description is complete. It covers what the tool does, how to use it in a broader workflow, and a key caveat about data interpretation. The presence of an output schema and annotations means the description does not need to explain return values or safety, satisfying the completeness requirement.

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 baseline is 4. The description does not need to explain parameters, and it does not attempt to; instead, it mentions the returned 'method' string, which is relevant for downstream usage. Since parameter semantics are not applicable, the baseline score 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 lists every ranked list published by the directory, with concrete examples like "Overall" and "3D Art in Poland". It specifies the exact data returned (size, URL, slug, method) and explicitly distinguishes itself from the sibling tool get_ranking, making its 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?

It explicitly instructs to use this tool before calling get_ranking, naming the sibling and providing a workflow. It also clarifies that lists are ordered by completeness, not studio quality, preventing misuse. The directive "Always pass the method on" gives actionable 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 readOnlyHint=true and idempotentHint=true, so the safety profile is known. The description adds valuable behavioral context: the types of documents searched (studio profiles, buyer guides, ranked lists, statistics page), the citable result format, and the relationship with the 'fetch' tool. However, it does not disclose potential limits like result count or ordering, so it falls short of a 5.

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 purpose and output format, followed by a concise alternative and next-step instruction. Every sentence adds value with no filler or repetition.

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, strong annotations, and an output schema. The description covers the key behavioral aspects: what it searches, what it returns, how to use results, and when to use an alternative. No significant gaps remain for an AI agent to select and invoke 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?

The single parameter 'query' already has an excellent schema description with examples. Schema coverage is 100%, so the description does not need to compensate. The tool description adds context about the result format but does not add meaning to the query parameter 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 clearly states the tool's function: 'Search this game development outsourcing directory and return matching documents' with specific document types listed and a concrete output format ('{id, title, url} results'). It also distinguishes from the sibling 'search_studios' by noting that the latter should be preferred for structured studio fields.

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?

Explicit usage guidance is provided: 'Prefer "search_studios" when you need structured studio fields such as services, engine or country.' Additionally, it instructs the next step: 'Pass the id of any result to "fetch" to read it in full.' This clearly indicates when to use this tool versus alternatives and how to proceed with results.

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 annotations already declare readOnlyHint=true and idempotentHint=true, so the description doesn't need to restate safety. It adds valuable behavioral details: returns up to 25 studios, includes profile URLs, and provides the true match count ('10 of 214') enabling accurate reporting. This goes beyond what annotations capture.

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 dense, front-loaded sentences. The first sentence states purpose and scope; the second adds usage guidance and return behavior. No redundant words or restatement of the 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 9-parameter optional-filter search tool with output schema and annotations, the description covers when to use it, what it returns (URLs, total count, up-to-25 limit), and how to phrase queries. It doesn't explain boolean combining of filters, but the schema and enums handle that. This is sufficient for the agent to select 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?

The input schema has 100% coverage with each parameter described, including enums and accepted input formats. The description merely summarizes the filterable dimensions without adding new semantics. It does clarify that free text searches name/tagline/description, which is already in the query param description. Since the schema carries the burden, 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 uses a specific verb 'Find' plus the resource 'game development outsourcing studios in this directory', and enumerates the filter dimensions (service, country, region, engine, etc.). It clearly distinguishes from sibling tools like 'get_studio' (single studio) and generic 'search' by framing this as the entry point for studio 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?

Explicitly says 'Start here for any ... question', giving clear when-to-use guidance for common user intents. It doesn't mention specific alternative tools or when-not-to-use, but the 'start here' phrasing provides a strong contextual cue. It also advises on how to report results ('instead of implying you have seen the whole directory'), which guides usage behavior.

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