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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses non-obvious behavior: settings are merged shallowly so only passed keys change, the block HTML is re-serialized, and the template plain-text body is regenerated as a side effect. It also warns that ids are position-based and only stable while order is unchanged. This is exactly the kind of consequence disclosure that 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?

Four densely packed sentences, front-loaded with purpose and behavior, and each one earns its place: the acquisition route, the merge rule, the side effects, and the id-stability caveat. No restatement of the tool name or 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?

For a mutating block-edit tool with no output schema, the description covers what is needed to call it correctly: required inputs, how to obtain the id, merge behavior, regeneration side effects, and id invalidation. Nothing a caller would need 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?

With schema coverage at 100%, the schema already carries the per-parameter detail, so the baseline is 3. The description adds real value on top by explaining the merge semantics of settings (only passed keys change) and giving a concrete example payload, which clarifies intended usage of the nested object beyond the schema text.

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 a specific verb+resource and an explicit scope ('Edit a single block in a template without touching the rest of the email'), which cleanly separates it from meisa_update_template, meisa_insert_template_block, meisa_delete_template_block and meisa_move_template_block. It also names the source of the required identifier, meisa_get_template_blocks, so the agent knows how to obtain a valid input.

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 states where the block_id comes from and gives a clear operational rule ('re-read after any insert/delete/move'), which is genuine when-to-use guidance for a position-based id scheme. It stops short of an explicit exclusion such as 'to change template-level metadata use meisa_update_template instead', leaving that routing to inference.

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