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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description earns full credit by going far beyond them: it discloses that this is a full replacement where omitted subjects are deleted, that an empty array wipes the plan, and — critically — that the call does not take effect but returns a link requiring user approval. That approval gate is a behavioral trait no annotation can express.

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 most consequential constraint (full replacement, omissions deleted) is front-loaded in the second sentence, which is the right call for a destructive tool. It loses a point for repetition: the instruction to read get_target_allocation first appears twice, once parenthetically under `dim` and again as the closing sentence.

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?

There is no output schema, and the description compensates by explaining exactly what the call returns (a user-approval link). Safety, replacement semantics, axis selection, deletion behavior, and the follow-up instruction to the user are all covered for a three-parameter destructive mutation.

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 baseline is 3; the description earns a bump by adding the empty-`rows` deletion convention, which the schema does not state, and by framing `dim` as an axis decision to verify via get_target_allocation. It leaves the `profile` parameter entirely to the schema, so it doesn't fully compensate on every field.

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 action on a specific resource ('propose a change to the user's target allocation') and immediately clarifies the mental model: the plan they mean to hold. It also distinguishes itself from every sibling by explaining the read/write pair with get_target_allocation and by naming the approval-link workflow that no sibling shares.

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?

Gives explicit when-to-use guidance ('Read get_target_allocation first'), explains how to choose between the two axes, covers the edge case (empty `rows` deletes the plan entirely), and tells the agent what to do afterwards ('tell them to open it'). Nothing about invocation is left to inference.

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