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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description does add real value with two behavioral facts annotations cannot carry: edits are gated on expected_version, and already-published releases retain their pinned metadata. It omits, however, whether retire is reversible, what the destructive path actually removes, or that the operation behaves as a full replacement requiring all seven fields.

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 compact sentences with the field enumeration front-loaded and the publishing caveat trailing as a qualifier. The first sentence duplicates the title verbatim, which is mild redundancy, but no sentence is filler.

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 destructive, eleven-parameter mutation with 18% schema coverage and no output schema, the description is thin. It does not address what happens to fields not supplied despite seven being required, whether retirement is undoable, permission or capability prerequisites, or what the call returns on a version conflict -- all things an agent needs before invoking it.

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 only 18% (company and idempotency_key), so the description must compensate, and it partially does: it maps the editable field list onto caption/alt_text/provenance/transcript/poster_asset_id and ties 'at the expected version' to the concurrency parameter. Unexplained remain the required `reason`, the `retired` boolean, and the null option on poster_asset_id, leaving several of eleven parameters without semantic guidance anywhere.

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 names a specific verb (edit/retire) and resource (guide media), and enumerates the mutable fields (captions, alt text, provenance, transcript, poster). That is enough to separate it from summer_assets_get, summer_assets_list and summer_assets_uploads_create without opening any schema, though no sibling is explicitly named.

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 for modifying or retiring media that already exists, and the 'published releases keep their pinned metadata' line hints at a scope limit. There is no explicit when-to-use, no when-not-to-use, and no pointer to a sibling such as summer_guides_save or summer_assets_uploads_create for the create path.

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