mail_read_message

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses the no-side-effect detail that the message is not marked as read, that HTML is converted to text with a size cap, and that attachments are listed but not downloaded. The prompt-injection warning about untrusted external content is exactly the kind of operational hazard an agent needs before consuming email bodies.

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 tight sentences: what it returns, what side effects it avoids, and the security caveat. The payload description is front-loaded and no sentence is filler — even the injection warning earns its place for an open-world read tool.

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?

With no output schema, the description fully specifies the return shape (sender, recipients, subject, date, text, attachment names) and notes the HTML-to-text conversion and truncation. Side effects, safety profile, and the uid provenance are all covered, leaving nothing an agent needs 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 both uid and folder are already documented, and the description's 'uid (de mail_list_messages)' largely restates the schema's own note. The 'tope de tamaño' remark hints at output truncation rather than parameter behavior. Baseline 3 is appropriate since the schema carries the parameter burden.

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 ('Lee un mensaje del correo institucional por uid') and then enumerates exactly what it returns: remitente, destinatarios, asunto, fecha, texto y adjuntos. It also names the sibling (mail_list_messages) that supplies the uid, so the agent can distinguish it from mail_search or mail_set_seen without 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?

The parenthetical '(de mail_list_messages)' makes the prerequisite flow explicit — you need a uid obtained from the listing tool — and 'Solo lectura: no marca el mensaje como leído' implicitly steers away from mail_set_seen. It lacks an explicit 'use X instead when...' clause for mail_search or a statement about when not to read a message, so it falls short of a 5.

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