shipyard

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

Adds behavioral constraints beyond annotations: reviews must be authentic and meet length minimum. Annotations already declare mutation (readOnlyHint=false), so description complements well.

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: first states purpose, second adds key constraints. Front-loaded, 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?

With 2 required params, no output schema, and annotations covering mutation, the description fully covers what, when-not, and constraints.

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 100%, so baseline 3. Description restates body minimum length (already in schema) but adds ethical nuance. No new parameter-level details.

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 'Post a review (comment) on a project' with a specific verb+resource. It clearly distinguishes from sibling tools like reply_to_review and like_project.

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?

Provides clear context about genuine use, no fabrication, and minimum length. Does not explicitly exclude alternatives but offers strong ethical 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?

The description discloses key behaviors beyond annotations: it's a write operation (consistent with readOnlyHint=false), non-idempotent (as implied by idempotentHint=false), charges wallet credit, never charges a card, and returns a top-up URL on short credit. This provides comprehensive understanding of side effects.

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 extremely concise with three front-loaded sentences. It first states the primary action, then explains the amount parameter, then specifies ownership and payment constraints. Every sentence earns its place without 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?

Given no output schema, the description effectively covers the tool's purpose, precondition (ownership), payment mechanism, failure mode (top-up), and parameter details. It provides sufficient context for an agent to correctly invoke the tool without needing additional information.

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 full coverage (100%) and clear descriptions for both parameters (amount as US dollars per review, project_id as id/slug). The description adds no new syntactic details beyond the schema, only behavioral context like ownership. 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 funds a paid review bounty on the user's own project, paying from wallet credit. This is a specific verb-resource combination (fund bounty) that is distinct from all sibling tools (add_review, get_project, etc.).

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 usage context: only project owners can use it, payment relies on wallet credit, and insufficient credit triggers a top-up URL. It lacks explicit comparison to alternatives or when-not-to-use scenarios, but the constraints are well articulated.

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, so safety is known. The description adds the behavioral detail that reviews are included inline, which supplements the annotations. No contradictions.

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 main purpose. No redundant or wasted words. Every sentence 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?

Given the low complexity (one parameter, no output schema, simple read operation), the description covers the essential behavior and return content. Could mention error handling for missing projects, but overall adequate.

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 'id_or_slug' is already well-described in the schema. The main description adds no further semantic detail about the parameter beyond what the schema provides, so 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?

Description clearly states the verb ('Fetch'), the resource ('project'), and the retrieval methods (by id, slug, or owner_handle/slug path). It also specifies that reviews are included inline, which distinguishes it from sibling tools like list_projects that return multiple projects.

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 when to use this tool (when needing a specific project with reviews) but does not explicitly state when not to use it or provide alternatives. Context is clear but lacks exclusions.

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

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

Annotations already provide idempotentHint=true and destructiveHint=false. Description adds the 'not a toggle' nuance, which is useful but not extensive.

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 action. Every word 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?

For a simple idempotent like operation with one parameter, the description and annotations fully cover behavior. No output schema needed.

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% for the single parameter 'project_id', which is clearly documented. The tool description does not add further parameter details beyond reinforcing meaning.

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?

Description uses specific verb ('Upvote') and resource ('project'), clearly stating the action. It distinguishes from sibling 'unlike_project' by noting idempotence and not being a toggle.

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?

Implies when to use: for liking, with the idempotent note clarifying repeated use. Could explicitly reference 'unlike_project' for removal, but the sibling list provides 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?

The annotations already declare readOnlyHint=true, so the agent knows it's safe. The description adds useful behavioral details: sorting defaults to 'new', mine requires an API key, and filtering options. 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?

The description is two sentences long with no wasted words. It front-loads the purpose and then details sorting, filters, and the mine parameter. Every sentence 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?

The description lacks mention of the limit parameter (default 20, max 100) and does not describe the output format. Given no output schema, these are gaps. However, for a simple list tool, the description is mostly adequate.

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 schema already documents each parameter. The description provides an overview but doesn't add significant meaning beyond what's in the schema for individual parameters. 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 identifies the tool as browsing or searching the Shipyard feed, which distinguishes it from siblings like get_project (single project) or action tools. The verb 'browse or search' is specific to the resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states when to use the tool (to browse/search the feed) and explains sorting, filtering, and the mine option. It doesn't explicitly state when not to use it, but the context with siblings implies alternatives. Overall, the usage context is clear.

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

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

Discloses that calling again edits the existing reply (matching idempotentHint), warns against fabricating fixes, and states the minimum length beyond what annotations provide.

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

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

Four sentences, front-loaded with purpose, no fluff. Every sentence adds essential information.

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

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

For a 3-parameter tool with no output schema, the description covers purpose, usage, behavioral nuances (edit behavior, ethics), and validation rule. Fully sufficient for an AI agent.

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 parameters. Description adds minimal parameter-level value beyond noting body min length, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb 'Answer a review', identifies the resource as a review on a project you own, and distinguishes from siblings by noting it's a reply, not an add. Includes practical guidance on content.

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?

Explains when to use (to answer a review on your project) and what to include (fixes, etc.). Mentions editing behavior and content warnings, but does not explicitly contrast with sibling tools like add_review.

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 indicate a non-read-only, non-idempotent write operation. The description adds that it creates a public listing (warning the agent of visibility) and specifies constraints for hero_image_url (must be public http(s) URL). 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?

Two sentences, no unnecessary words. The purpose and critical usage warning are front-loaded. 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 7-parameter tool with no output schema, the description covers the main functionality, critical pre-conditions, and a key parameter constraint. It lacks details about the return value or success/failure behavior, but the essentials for invocation are present.

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 adds value by emphasizing the need for user confirmation on the required parameters and explaining the hero_image_url constraint in detail, including a workaround for local files. This goes beyond the schema's basic descriptions.

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 publishes a new project under the user's account. It specifies the action ('Publish') and resource ('project'), and the IMPORTANT note distinguishes this as a creation tool from sibling tools like 'get_project' or 'list_projects'.

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 instructs the agent to confirm title, pitch, url, and category with the user before posting, emphasizing the public nature of the listing. It also advises using the CLI for local images, providing clear context. While it doesn't explicitly list when not to use, the sibling context offers 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?

Explicitly states idempotency and no-op behavior for unliked projects, consistent with idempotentHint=true. 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 short, front-loaded sentences with no wasted words.

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

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

Adequate for a simple idempotent tool with one param and no output schema. Idempotency detail covers behavioral edge 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?

Only one parameter, schema description coverage 100%. Description adds no extra meaning beyond what schema 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?

Clear verb+resource: 'Remove your upvote from a project.' Distinct from sibling tool like_project (adds upvote).

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?

Implied usage: use when you want to remove a like. No explicit guidance on when not to use or mention of alternatives like like_project.

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, so the description adds context about what is displayed (balance and ledger entries) and mentions credit funds and top-up location. This is adequate but does not elaborate on ledger detail or update frequency.

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: first clearly states the tool's output, second provides useful context about credits and top-up. No wasted words.

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

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

The description covers the main purpose, but lacks details on ledger entry fields, pagination, or date range. For a simple balance tool, this is acceptable but not fully complete.

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

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

There are zero parameters, so schema coverage is 100%. Description adds no parameter info, but none is needed. Baseline 4 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 clearly states the tool provides wallet balance and recent ledger entries, which distinguishes it from all sibling tools that focus on reviews, projects, and funding actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for checking balance and ledger entries, but does not explicitly state when not to use or mention alternatives. Since it's the only wallet tool, the context is clear.

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