CasaCaddy Maintenance

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description earns credit by disclosing a privacy boundary not present in any structured field — no device identifier, billing data, home library, appliance list or task history is exposed — which meaningfully constrains agent expectations about the payload.

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 waste: the purpose leads, and the privacy scope follows as a necessary qualifier. Nothing is repeated from the schema or annotations.

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 an output schema present, return values need not be described, and with zero parameters the input surface is trivially complete. The only remaining gap is sibling differentiation against get_maintenance_guide and get_saved_guide_request, which is unaddressed.

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 takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. Schema coverage is 100% and no argument semantics are needed.

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 ("Identify the linked CasaCaddy Pro installation") plus a second concrete output dimension ("current maintenance-guide allowance"), so the agent knows exactly what this retrieves. It never names or contrasts the siblings get_maintenance_guide / get_saved_guide_request, so sibling differentiation is left implicit.

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?

Usage is only implied: the mention of an installation and its guide allowance hints at checking linkage status/quota, but there is no explicit when-to-use statement, no exclusions, and no routing to the guide-fetching siblings. Adequate but with a clear gap for an agent choosing among three 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?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), it discloses metering economics (a fresh guide consumes Pro allowance, exact-cached guides are unmetered), the underlying pipeline, and idempotency behavior (identical request_key results are persisted, so retries never start a second provider request). This is rich operational context an agent could not derive from the structured fields.

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 core action and its prerequisite are front-loaded, and every sentence carries information (metering, retry key, safety fields, boundaries). It is dense rather than wasteful, though the run-on sentences pack several distinct behaviors together without visual breaks.

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 an output schema already exists, the description needn't explain return values, and it covers the important gaps: prerequisites, metering, idempotency, and scope boundaries. Only the required 'item' payload semantics remain unaddressed for a fairly complex nested 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 0%, so the description must carry the load. It adds strong meaning for request_key (fresh UUID, reuse on retry, persistence) and use_existing_allowance (confirmation before consuming allowance), but says nothing about the required nested 'item' object or its category/brand/model/specs fields, leaving that half of the parameters undocumented.

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 gives a specific verb and resource: 'request a maintenance guide for the appliance details and question the user supplied.' It also draws a boundary ('does not read on-device appliances or schedule tasks'), though it never names the sibling tools get_connected_installation or get_saved_guide_request, so cross-tool routing 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?

It states the precondition (a linked Pro installation), a procedural instruction ('Ask for confirmation before using existing Pro allowance'), and retry guidance ('reuse it for retries'). It is clear about usage context, but stops short of naming the alternatives an agent should pick instead.

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 readOnly/non-destructive/closed-world, and the description still layers on real behavioral detail: 30-day retention, scoping to the linked installation, and the absence of side effects (no generation, no allowance consumption, no on-device library read). That is meaningful disclosure beyond the structured fields.

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?

Front-loaded identity and scope, then constraints, then side-effect exclusions — nearly every sentence earns its place. The closing 'Keep all safety warnings and professional-help boundaries intact' is an instruction about relaying content rather than tool selection, so it is slightly off-purpose.

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 an output schema present, return values need not be described, and the description still supplies retention window, access scoping, and side-effect profile. An agent has everything needed to call this 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 0%, so the description must carry the parameter alone. It specifies that the key is the 'exact request_key' tied to that installation, adding matching semantics; the uuid format is left to the schema, which is acceptable for a single required parameter.

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?

Precise verb+resource: 'Recover one maintenance-guide request made through MCP by the linked installation, using its exact request_key.' The scope (single record, this installation, 30-day window) makes it easy to distinguish from get_maintenance_guide, though the siblings are never named 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?

'using its exact request_key' and 'Only that installation's request records are returned' give clear conditions for use, and the negative clause ('Does not start generation, consume allowance or read the on-device library') tells the agent when not to pick this. No sibling is named as the alternative, which keeps it 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.