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

Annotations declare a non-read-only, non-destructive mutation, and the description adds the key behavioral nuance — it only fills *empty* areas, so it will not clobber existing content, and markdown formatting is honored. It does not say what happens on a name mismatch or repeated fills.

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 the operation, then the name contract, then the precondition. Nothing is redundant with the title or schema.

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?

Covers the mutation semantics, the naming contract, and the outline-first workflow for a tool with no output schema. Missing only edge-case behavior (unknown stub names, whether re-filling an already-filled area overwrites or errors).

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%, so the baseline is 3, but the description adds real semantics beyond it: `texts` keys must be the *exact* stub names surfaced by the outline, and values accept markdown bullets. That name-matching constraint is not in the schema.

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 and resource with its distinguishing scope: it fills only a slide's *empty layout* text areas, keyed by name. An agent can tell it apart from napkin_slide_update or napkin_deck_write without opening any 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?

Gives a clear precondition and workflow: read the outline first to see which stubs remain open, then pass those exact names. It names napkin_deck_outline as the source of truth, but does not state when not to use it (e.g. for non-stub content, use slide_update).

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