tempo_update_plan

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

This is a strong disclosure of non-obvious behavior beyond the destructiveHint annotation. It explains that despite Tempo's PUT replacing the entire resource, the tool performs a read-merge-write, that a preview shows the full merged body, that concurrent modifications cause refusal rather than overwrite, and that confirmation can take two forms depending on client capability. These are exactly the behavioral traits an agent cannot infer from the schema or 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?

The description is long but every sentence carries essential operational information. The most important guidance — update by id, supply only changed fields — is front-loaded, and the confirmation/token complexities are explained in a logical sequence. There is no filler or repetition of schema details.

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 16-parameter mutation with no output schema, the description covers what matters most: partial-update semantics, preview behavior, conflict refusal, and the full confirmation protocol including the fallback token path. An agent has enough information to call the tool correctly and handle both the elicitation-supported and fallback confirmation modes. The absence of an output schema is mitigated by the detailed description of what the preview and confirmation responses contain.

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 every parameter. The description adds meaningful parameter-level semantics on top: omitting a field preserves its current value, only changed fields should be supplied, and confirmToken has strict lifecycle rules including 'same arguments' on the repeat call. This goes beyond the baseline expected when the schema already covers parameter 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?

The description opens with a specific verb and resource: 'Update an existing Tempo plan (resource allocation) by id.' It clearly distinguishes this from sibling create/delete/get plan tools by emphasizing that only changed fields are supplied and that the resource must already exist. The target object (Tempo plan) and the operation (in-place update with merge semantics) are unambiguous.

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 explicitly tells the agent when and how to use the tool: only for updating existing plans, supply only changed fields, expect a confirmation flow, and in the fallback path require a confirmToken from a prior preview only after explicit user approval. It also warns the caller against inventing, reusing, or sending confirmToken on the first call, and notes when it is ignored. This provides clear context for using the tool and the two-step flow, though it does not spell out trivial exclusions like 'use create_plan for new plans' — the 'existing plan' wording makes that implicit.

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