hydra_load

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description doesn't contradict them nastead it adds valuable context: the refusal condition (human-written blocks unless take=true), the warning to save first, and the dry run/hush behavior. It also mentions that unknown names return a list of saved sketches, which is beyond the annotation coverage. This adds meaningful behavioral detail beyond the 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?

There are only four sentences, each carrying substantial information: the main action, the refusal condition, a caution to save, and behavior on unknown names. The description is front-loaded with the core purpose and then essential safety/edge-case info. No unnecessary fluff.

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?

The description covers main purpose, refusal condition, safety tip, and edge case return. However, it doesn't describe the return value for successful loads or the content of the returned list for unknown names dozen. Given the output schema exists, the description needn't detail return values, but more clarity on the refusal outcome (does it error or return a message?) would complete the picture. Still, for a 3-param tool with annotations covering safety, it's reasonably complete.

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 0%, meaning the schema provides no descriptions for any of the parameters. The description mentions 'take' in the context of overriding human-written blocks, and 'name' is implied, but 'validate' is not addressed at all. With zero coverage, the description should explain all parameters, especially 'validate' which has a default and is not self-explanatory.

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 clearly states the action (replace composition with a saved sketch) and the specific resource (saved sketch). It also mentions key behaviors like dry run, hush, and keeping author, which helps distinguish it from similar tools like hydra_sketch, though it doesn't explicitly name all siblings that might overlap.

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?

It provides explicit conditions for when to use the tool (replacing composition with saved sketch, similar to hydra_sketch) and when it will be refused (if human-written blocks exist unless take=true). It also advises to save the current piece first if worth keeping, but doesn't explicitly mention alternatives beyond the implied hydra_sketch.

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