gardener_apply

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

Annotations already mark destructiveHint=true and readOnlyHint=false; the description goes further by detailing exactly what destructive effects occur per action (e.g., 'retire the memory', 'discards this proposal and the evidence behind it', 'blocks the pattern permanently'). It also states both dismiss and hide are reversible by the owner, adding context not available from 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 dense but every sentence earns its place. It uses semicolons to compactly list the many apply sub-actions, and the dismiss/hide contrast is explained in two sentences without fluff. The structure moves from general purpose to specific actions to preference guidance, which is organized and easy to 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?

For a complex mutation tool with no output schema, the description thoroughly covers the tool's effects across all actions and gives reversal guidance. However, it does not state what the tool returns on success (e.g., the resolved proposal, a confirmation, or the updated proposal list), which leaves a small gap given there is no output schema to fill it.

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 covers 100% of parameters with basic descriptions, but the description expands the 'action' enum by explaining what each action does (apply with its sub-cases, dismiss meaning discard evidence and re-raise on recurrence, hide meaning permanent block). This gives the model semantic understanding of the parameter values beyond the schema's one-line notes.

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 'Resolve a gardener proposal' and then enumerates every action variant with concrete effects (archive->retire, merge->supersede, etc.), clearly distinguishing this from sibling tools like gardener_proposals (list) and gardener_request. The verb 'Resolve' is specific to acting on an existing proposal.

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 explicitly says 'Prefer dismiss unless the suggestion is wrong in principle rather than wrong for now', giving a decision rule for reject options. It also distinguishes apply vs dismiss vs hide by their consequences. While it doesn't name alternatives like gardener_proposals, it clearly implies this tool is the resolution step after viewing proposals, so the usage context is well defined.

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