Shiped

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

No annotations exist, so the description carries the full burden. It discloses the human-approval requirement and the retry-after-approval workflow, which is non-obvious behavior. It stops short of stating irreversibility or permission requirements outright.

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 waste. The destructive action is front-loaded and the approval mechanic follows immediately.

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?

No output schema, but the description covers the one non-trivial response behavior an agent must handle (approval request). For a single-parameter delete this is close to complete, missing only explicit irreversibility.

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, slug, and schema coverage is 100% with its own description ('Project slug to delete'). The description adds no semantics beyond the schema, so the baseline 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?

States a specific verb and resource: 'Delete a deployed project from Shiped.' An agent can tell this is a destructive operation distinct from deploy_to_shiped and list_shiped_projects, though it never names those siblings explicitly.

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 the approval gating and what to do when approval is requested — relay link, retry after approval. That is real procedural guidance, but there is no statement of when not to use it or prerequisites beyond approval.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does reveal the key traits — the operation creates a live deployment and returns a public URL. But it omits substantial behavioral details for a mutation tool: what happens if the subdomain/name already exists, whether redeployment overwrites an existing project, and the oneOf requirement to pass exactly one of html or files. It also scopes itself to 'HTML/CSS/JS' while the schema supports node and python types.

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 with zero filler: the first states the action and outcome, the second supplies the triggering context. The most decision-relevant fact — instant public HTTPS URL — is front-loaded in the opening clause.

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 schema fully documents all parameters and the oneOf constraint, and the description supplies the headline return value (public URL). However, with no annotations and no output schema, the agent is left without failure-mode information (e.g., name collisions, overwrite behavior) and without awareness that node/python deployments are supported — significant for a tool whose sibling delete_shiped_project implies a lifecycle the description never touches.

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%; every parameter (html, name, type, files) already has a clear description including the subdomain mapping and the static/node/python semantics. The description text itself adds no parameter-level meaning beyond the schema, so the coverage-based 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 opens with a specific verb and resource — 'Deploy HTML/CSS/JS code to Shiped' — and names a concrete outcome, 'an instant public HTTPS URL.' The deploy verb cleanly differentiates it from the sibling tools delete_shiped_project and list_shiped_projects. The narrowing to HTML/CSS/JS (schema also allows node/python) doesn't obscure the core 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 second sentence gives explicit context for when this tool is the right choice: 'Use after generating code with an AI to make it live and shareable.' This makes the deploy-vs-manage distinction against the delete/list siblings evident, though it stops short of naming alternatives or stating explicit when-not-to-use conditions.

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

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

No annotations are provided, so the description must carry the behavioral disclosure. 'List' clearly signals a read-only operation, and the description states what is returned. However, it does not mention authentication expectations, pagination, error conditions, or whether an empty list is possible. For a zero-parameter read-only tool this is adequate but not rich.

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

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

The description is a single sentence with no filler. It is front-loaded with the action 'List' and immediately states the resource and output. Every word contributes meaningful 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 simple zero-parameter list with no output schema, the description adequately conveys scope ('user's deployed projects') and content ('URLs'). It could go further by describing the response shape or auth context, but the low complexity means no serious information gap exists.

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 and the schema is empty, so there are no parameter semantics to explain. Per the rubric, a zero-parameter tool gets a baseline of 4 because the description cannot be expected to add parameter-level detail.

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 names a specific verb ('List'), a specific resource ('deployed projects on Shiped'), and the output ('their URLs'). It is immediately distinguishable from sibling tools like delete_shiped_project and deploy_to_shiped because the operation is clearly a read-only listing.

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 conveys the basic context: it lists the user's deployed projects. It does not explicitly state when to prefer this tool over the delete or deploy siblings, though the tool names imply the appropriate use case. No exclusions or alternative routing are provided.

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