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

The readOnlyHint annotation only tells the agent this is non-mutating; the description layers on the substantive semantics that matter: the vote is resized rather than cleared, fees are not discarded, no NFT is burned, and the added stake inherits the existing lock end so it cannot be withdrawn early. That is exactly the kind of consequence-level detail an agent cannot derive from annotations or schema, and it is consistent with a prepare-only tool.

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?

Three sentences, front-loaded with what is produced, then the non-destructive guarantees, then the lock-end consequence. Every sentence adds information and none restates the tool name or the schema.

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 explained, and the description covers the mutation semantics and the approval/native value it prepares. What is missing is the precondition set — that the caller must hold the veNFT and have the stake token approved — which for a prepare tool of this complexity would be worth one clause.

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%, so the six parameters (including chain_id's direction to get_ve33_allocations and the base-unit note for amount) are already documented. The description adds one useful semantic — the added stake adopts the NFT's existing lock end — but says nothing extra about stake_token, sender, or ve_id beyond the schema. Baseline 3 is correct when the schema carries the load.

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 states a specific verb ('prepare'), a specific resource ('increase a ve-token stake'), and even names the resulting contract call (increaseStakeAmount). That is enough for an agent to know what it produces. It stops short of naming the sibling it is not (e.g. prepare_ve33_stake for a brand-new lock or prepare_ve33_extend), so differentiation is inferable rather than explicit.

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: 'preserving the existing vote and fee accounting' signals this is for adding to an existing locked position rather than creating one, but the description never says when to pick this over prepare_ve33_stake, prepare_ve33_extend, or prepare_ve33_merge. No prerequisites (ownership of the veNFT, approval of the stake token) are stated. An agent can guess the context but is not routed.

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