red-castle

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered. The description adds only the ownership scoping ('your'), and says nothing about behavior when a request is still pending, completed, or the ID is unknown.

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?

A single short sentence with no filler, and the verb plus resource are front-loaded.

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 tool with no output schema, the agent still doesn't know what 'status' contains (states, fields, terminal vs in-progress values) or how to interpret a pending request, which is exactly what the tool exists to reveal.

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?

One required parameter with 0% schema description coverage, so the description must carry the burden. 'One of your deletion requests' hints at the ID's origin and ownership, but no format, source tool, or error behavior is given for request_id.

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?

Specific verb ('Show') and resource ('the current status of one of your deletion requests'), which an agent can distinguish from the sibling tools that create or list requests. It never names those siblings explicitly, so differentiation relies on inference.

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 phrase 'one of your deletion requests' implies a request_id obtained from request_deletion or list_my_deletion_requests, but the description gives no explicit when-to-use, no deadline/retention context, and no mention of 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuinely new behavioral fact — results are ordered newest first — but says nothing about pagination, result caps, or what happens when the status filter matches nothing.

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?

One short front-loaded sentence containing no filler, and the sort order is stated up front. It is efficient but arguably undersized for a tool with an optional filter parameter.

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 output schema and no per-parameter documentation, the description is the only place the status filter could be explained, and it is silent. Annotations cover the read-only nature, but an agent still lacks enough to know how filtering and pagination behave.

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 'status' parameter has 0% schema description coverage; only the enum values are documented. The description never mentions that filtering by status is possible, so the agent must reverse-engineer the parameter's purpose from its name and enum alone.

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 ('List') and resource ('your deletion requests') plus an ordering guarantee ('newest first'), and the possessive 'your' implicitly scopes results to the caller. It does not explicitly contrast with siblings like list_objects or get_deletion_request, so an agent must infer the boundary from the plural/singular split.

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?

There is no statement of when to use this tool versus list_objects (for live objects) or get_deletion_request (for a single request), and no prerequisites or exclusions. Usage is only implied by the name and the word 'deletion'.

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 readOnlyHint=true and openWorldHint=false. The description adds useful behavioral context about visibility scoping—quarantined objects are hidden—but says nothing about pagination, ordering, permissions, or how hidden objects relate to the sibling deletion-request tools.

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 sentences, front-loaded with the core action and followed by the key visibility constraint. There is no wasted wording.

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 listing tool this is close to adequate, but with no output schema the description does not indicate the return shape, pagination behavior, or whether an empty result is possible—details an agent might need to use the results 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%, and the single prefix parameter is documented in the schema with an example. The description adds no parameter semantics beyond that, which is acceptable given the schema already carries the burden.

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+resource: 'List the objects you can see.' It is clearly a listing tool and is distinct from the deletion-request siblings, though it does not explicitly contrast with them.

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?

There is no explicit guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The implicit usage is obvious for a list tool, but the description provides no real routing 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?

Adds substantial behavior beyond the annotations: the deletion is not immediate, the object is hidden in quarantine, and a human either approves permanent deletion or restores it. This resolves the potentially confusing combination of destructiveHint=false with a deletion tool and tells the agent the real-world lifecycle effect.

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 short sentences, each earning its place: what it does, the quarantine/approval consequence, and how to follow up. The key behavioral fact (nothing is deleted right away) is front-loaded.

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 mutation tool with annotated safety hints and no output schema, the description covers the lifecycle and the follow-up tool. It stops short of saying what identifier or object reference the agent should use with get_deletion_request, a minor remaining 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 description coverage is 100%, so reason, object_key, and risk_score are already well documented in the schema, including that the human reads the reason and the 0-100 risk scale. The description only implies 'one object' and adds no further parameter guidance, so 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 ('Ask Red Castle to delete one object') with explicit scope of exactly one object. It also differentiates the follow-up path by naming get_deletion_request, so an agent can distinguish it from siblings without opening schemas.

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?

Clearly establishes the context of use (requesting deletion of an object) and points to get_deletion_request for follow-up. It does not state explicit exclusions such as when to use list_my_deletion_requests or when not to request deletion, so it falls short of a full when/when-not treatment.

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