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

Beyond readOnlyHint=true, the description discloses non-obvious behavior: durations are measured from now and floored to a week boundary, sub-week requests are refused rather than signed, and a read bundle is fetched to reject impossible actions before signing. That 'builds but never signs or submits' framing is exactly the context an agent needs, though it says nothing about what the returned action contains or whether it must be re-validated.

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, both front-loaded with the most important information (what it builds, then the duration and validation rules). Dense but no filler; the middle clause listing action types is slightly redundant with the enum but earns its place as a quick scan.

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?

An output schema exists so return values needn't be explained. Given six parameters with an enum and only a readOnlyHint annotation, the description supplies the missing behavioral layer — duration rounding, refusal instead of signing, and pre-signing state checks — leaving nothing important unsaid for correct invocation.

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 every parameter already carries its own description including the week-floor and four-year cap. The description restates those rules and clarifies which actions are relevant per field only implicitly; it adds little machine-relevant meaning beyond the schema, so the baseline of 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?

The description opens with a specific verb and resource ('Build one veAERO escrow action') and then enumerates every operation the tool covers: create, increase, extend, toggle permanent, withdraw. That enumeration matches the action enum and lets an agent distinguish this from the many sibling prepare_* tools without opening the schema.

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 implied through the action list and the statement that impossible actions are caught before signing, which tells the agent this is a build-and-validate step. However, it never names alternatives — notably prepare_ve33_extend, prepare_ve33_withdraw, prepare_ve33_stake and prepare_aerodrome_sugar_reads sit adjacent and an agent gets no explicit rule for choosing between them.

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