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

Beyond the annotations it discloses real behavior: the write is scoped to the caller's own record, nothing else changes, it is reversible from the same surface, and it returns an ordinary result rather than a plan_token. The one tension is that it frames the action as harmless and auto-approved while destructiveHint=true, which an agent may read as a stronger warning than the text implies; this is a mismatch in emphasis rather than a flat contradiction, since the description does acknowledge a write.

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?

The opening sentence is well front-loaded, but the confirmation boilerplate is repetitive: 'Auto-approved', 'runs immediately', 'taken as the instruction', and 'not a plan_token' restate the same point three times. The closing sentence about destructive/outbound/financial tools describes other tools rather than this one and dilutes focus.

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 one-parameter, no-output-schema tool, the behavioral picture (immediate execution, self-scoped write, undo path, plain result) is largely complete. The remaining gap is the unexplained material_id, which leaves an agent guessing at the one input it must supply.

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 0% and the description never mentions material_id, so nothing explains what the identifier refers to, where it comes from, or what happens if it names a material the caller has not opened. With a single undocumented parameter, the description should have compensated and does not.

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 and resource: 'Record that the caller has watched or listened to a material.' That is clearly distinct from read-oriented siblings such as language_list_materials or language_get_material. It stops short of naming an alternative, but the action itself is unambiguous.

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 explains when the tool fires ('runs immediately when the caller asks for it') and that the caller's request is taken as the instruction. That is execution policy, not selection guidance: it never says when to prefer this over language_add_material or how to obtain a material_id first. Usage is implied rather than directed.

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