peaka_update_cache

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

The description discloses two non-obvious behaviors beyond what annotations convey: the endpoint 'replaces — not merges — the schedules, so both incrementalSchedule and fullRefreshSchedule must be supplied with the full intended state every call,' and the warning that 'the backend may clamp to its allowed range — check it.' These are exactly the behavioral traits an agent needs to avoid sending partial updates or assuming the response equals the request. The annotations (idempotentHint=true, destructiveHint=false, readOnlyHint=false) are fully consistent, so 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 purpose is front-loaded in the first sentence, followed by the critical replace semantics, schedule format, clamping warning, and projectId workflow — each sentence earns its place. It is not a 5 because the ISO-8601 examples (PT6H, P1D, P7D, P30D) duplicate what the schema already provides, and the two projectId sentences could be merged without losing 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?

With no output schema present, the description compensates by telling the agent that 'the response reflects the schedule actually applied' and to check it due to clamping — the most important return-value behavior. Combined with the schema covering cacheId sourcing ('Available from peaka_get_cache_statuses') and the description covering prerequisites, replace semantics, and schedule formats, the essential calling information is present. It stops short of 5 because the response shape is only sketched and failure-mode behavior is not addressed.

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 schema already documents each parameter's meaning, format (BASIC with ISO-8601 pattern, or NONE), and replace behavior, so the baseline is 3. The description adds value by emphasizing that both schedules must carry the full intended state on every call (clarifying their interaction) and by noting the applied value may be clamped, which affects how the agent should interpret the parameters it sent. This modest but real increment justifies a 4.

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: 'Update cache settings on an existing cache in the Peaka project.' This is clearly distinct from sibling tools like peaka_create_cache, peaka_delete_cache, and peaka_refresh_cache_full/incremental, which operate on cache lifecycle and data refresh rather than schedule settings. The 'replaces — not merges — the schedules' detail further sharpens the scope beyond a generic update.

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 workflow guidance: 'If you do not already know the projectId for the current task, call peaka_list_projects first and ask the user which project to use,' plus a session-memory instruction to remember the chosen projectId. However, it does not explicitly draw when-not-to-use boundaries against the sibling refresh tools (e.g., when the intent is to trigger a refresh rather than change schedule settings), so the contrast with alternatives is implied rather than stated.

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