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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds real behavior beyond that — props a block type does not support (e.g. 'link' on a code block) are silently skipped, the 'inside' form cascades to every block within a rectangle, and the call returns the slide with its block ids. Minor caveat: the tool can delete blocks while destructiveHint=false, which is worth noting but is echoed by the annotation's own title, so it reads as an internal annotation nuance rather than a description/annotation contradiction.

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 one-line purpose, then organized by the three mode keys that match the schema properties. It is dense — nested parentheses and quoted pseudo-JSON make it run-on — but every clause carries operational meaning and nothing is repeated from the annotations.

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 6-parameter tool with array-of-object payloads, the description covers all three modes, placement defaults, prop-skipping edge cases, and even the return shape, while an output schema exists to carry structured returns. Nothing an agent needs to invoke it correctly 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 description coverage is 100%, so the baseline is 3. The description goes further than the schema by explaining the semantics the schema only names: 'inside' targeting a card's background block and all blocks in its rectangle, the 'ids' bulk-prop form, and the at_bottom placement default. That is meaningful added meaning over the property strings.

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 opening sentence names a specific verb and resource — 'Change some blocks of a slide and leave the others alone, in one step' — which is a block-scoped edit, clearly distinct from the sibling update_slide/add_slide. The three supported operations (add/update/delete) are enumerated with their payload shapes, so an agent knows exactly what the tool does before opening the schema.

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 gives clear in-tool context for each mode: add places on top unless at_bottom is set; update changes only the supplied props, and supports three addressing forms (single id, ids list, or inside a card). What is missing is any statement of when to prefer this over siblings such as update_slide or add_slide — no exclusions or alternatives are named.

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