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

Annotations already declare idempotentHint=true and destructiveHint=true, so the safety profile is carried structurally. The description adds genuinely non-obvious behavior: the text is shared by every post and platform publishing the file, and some networks do not support alt text — real blast-radius and caveat information not present in annotations.

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 sentences, zero filler: the scope statement comes first and the discovery pointer second. Every clause carries information an agent cannot get from the 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?

Return values are covered by an output schema and idempotency/destructiveness by annotations, so the remaining burden is scope and side effects — both addressed. Minor gap: it does not say whether clearing alt text affects already-published posts immediately or only future publishes.

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%, with altText null/empty-string clearing and organizationId's multi-org rule fully documented in the schema. The description's file-level propagation note adds semantic meaning to altText, but it says nothing about mediaId or organizationId beyond what the schema already states, so the baseline of 3 applies.

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 ('Set or clear the alternative text of a library image or video') and immediately distinguishes the scope from sibling mutation tools by noting it belongs to the file, not a post — implicitly contrasting with update_post.

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 concrete discovery path ('Use list_media to see which files have none') and clarifies the file-level vs post-level scope, which is the key selection decision here. It does not state exclusions or prerequisites (e.g., permission needs) but the context is clear enough to route correctly.

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