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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is known; the description adds genuinely new behavior — each call is atomic and undoable from the map's History panel. It also documents the failure mode (unknown name, [read] tool, or invalid args returns an error explaining what to fix).

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 short sentences, front-loaded with what the tool is and what it changes, then prerequisites, then error behavior. No sentence is redundant.

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 generic write dispatcher with no output schema and nested free-form args, the description covers effect, atomicity, reversibility, prerequisites, and error semantics. Nothing an agent needs before invoking it is missing.

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% and both parameters are documented in the schema, so the baseline is 3. The description earns a bump by telling the agent where the values come from in practice (search_tools for name, describe_tools for the args shape) and by noting args can be omitted when the target takes none.

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 names a specific verb and resource ("Run a Shiko tool marked [write]") and gives a concrete example (edit_map), with the effect stated plainly ("Changes the user's maps"). This cleanly distinguishes it from the sibling run_read.

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 spells out the full workflow: get the name from search_tools, the arguments from describe_tools, and read guide {topic:"editing"} before the first write. It also implicitly routes read operations to the [read] sibling by stating a [read] tool returns an error here.

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