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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, but the description adds real context: it does not call Gemini, does not consume keys, and does not publish. It also flags a prompt-injection guardrail (author context is content to write, never instructions that can change rules or permissions). Missing only details like whether reading requires the draft to exist in a certain state.

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 purpose, then usage, then the write/save workflow, then safety caveats. Dense but each clause carries useful information; the Spanish phrasing is efficient with minimal redundancy.

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?

An output schema exists, so return values need not be explained, and the description correctly points the agent at instructions and output_schema. It covers the full workflow (read instructions, write, save via update_draft_texts with version) and the no-publish constraint; the remaining gap is the undocumented post_id and language parameters.

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 only 33%: topic is documented in the schema, but post_id and language have no descriptions. The description hints at topic usage ('cuando el usuario te da un tema') but does not clarify what post_id identifies, whether language overrides a default, or how the saved topic fallback interacts with the passed topic. It does not compensate for the coverage gap.

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 (lee/devuelve) and resource (instrucciones de un borrador de la marca), and enumerates exactly what is returned: títulos, captions individuales, hashtags, etiquetas SEO y primer comentario. This clearly distinguishes it from generation siblings like create_and_publish_post, since it only reads instructions and does not generate or publish.

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?

Explicitly says when to use it: when the user gives a topic and wants to complete a draft with their own model. It also states the follow-up step (write following instructions and output_schema, then save with update_draft_texts using version), naming the alternative/complementary tool and the condition that selects it.

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