Delete blocks

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

Goes well beyond the annotations, which only declare it destructive, idempotent, non-read-only, and closed-world. The description explains the reference/diagnostic interaction (dangling refs surface as diagnostics but do not block), the no-op semantics of unmatched ids, the return envelope fields, the meaning of `notes`, and the refusal shape (`ok: false` with a `hint`, file unchanged). These are behavioral traits annotations cannot convey.

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?

Front-loaded with the core action and two routing alternatives in the first sentence, then layers in reference semantics, idempotency, and return/refusal shapes in tight, information-dense sentences. No filler.

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 no output schema, the description carries the return-shape burden and does so completely: lists `{ok, file, diagnostics, revision}`, explains `notes` and the `ok: false` refusal path. It also covers the reference-repair workflow that would otherwise be a common agent pitfall. Nothing material to correct invocation 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 the schema already documents both `file` (with an example path) and `ids` (block ids to remove). The description still adds meaning by clarifying that multiple ids are removed in one call and that non-matching ids are skipped — a subtle semantic not present in the schema. Slightly above baseline because it illuminates batch/id-miss behavior.

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?

States a specific verb (remove) and resource (blocks) with the key constraint 'by id'. It distinguishes itself from siblings by explicitly naming geml_revert (undo) and geml_set (change rather than remove), so an agent can route correctly without inspecting schemas.

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?

Explicit alternatives are named with the conditions that select them: geml_revert for undo, geml_set for changing rather than removing. It also specifies that dangling references produce diagnostics but don't block, and that unmatched ids are silently skipped, telling the agent what to expect in both the success and no-op paths.

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