create_quote_post

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

Annotations already declare this is a non-destructive, non-read-only, closed-world write, so the description only needs to add context. "No default person or auto-correction" is genuinely useful — it warns the agent that omitted or wrong speaker data will not be repaired. However, nothing is said about verification flags (quoteVerified, factsVerified), draft/final behavior, or what is produced and where.

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?

Two tight sentences with the action front-loaded and zero filler. The efficiency is partly achieved by omission rather than by disciplined writing, but nothing present 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?

A tool that takes a nested object of ~35 properties with no schema descriptions and no output schema is described in two sentences covering three fields. For a generation tool with enum templates, quality-verification booleans, and an outputFileName parameter, an agent lacks the guidance needed to populate the payload or anticipate the result.

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 0% across a deeply nested content object with roughly three dozen properties, so the description must carry the explanatory burden and largely does not. It clarifies only portrait, personName, and personTitle (and the template enum), leaving scene, callouts, sources, crop polygons, and quality-gate flags entirely undocumented. The "no auto-correction" line does add real meaning to the person fields, which keeps this above a 1.

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 gives a specific verb ("Create") and names the exact artifacts produced (quote_side or quote_overlay), which lets an agent distinguish this from create_cutout_post, create_photo_scene_post, and create_social_post. It stops short of a full statement of what the rendered output is (image? draft file?) or how it differs from create_social_post when the template happens to be a quote layout.

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?

Usage is only implied: the agent can infer this is the tool for quote-format templates, and the clause about portrait/speaker name/title signals prerequisites. There is no explicit when-to-use versus siblings, no mention of draft vs final mode, and no statement of what to do when the portrait is unavailable.

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