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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description earns credit for scoping that destructiveness — the recycle-bin soft delete only fires via autoArchiveOnExpiry — plus stating the file itself is never modified. It also discloses the required `media.edit` permission, which annotations do not cover. It stops short of describing the response form, though an output schema exists.

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 sentences, front-loaded with the mutation scope, then the merge semantics, then the sibling exclusion and the permission requirement. No filler, no repetition of the title, and the most decision-relevant clause comes first.

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 an 8-parameter mutation tool with full schema coverage, an output schema, and rich annotations, the description supplies everything else an agent needs: partial-update semantics, the destructive edge case, the alternative tool, and the auth requirement. Nothing material is left to inference.

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%, including the enum and null-clearing semantics for fit, altText, folderId and expiresAt, so the schema already carries the parameter burden. The description's field list is largely a restatement of those parameters rather than new syntax or format detail. Baseline 3 applies when the schema does the heavy lifting.

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+resource ('Update a media asset's metadata') and enumerates the dimensions it can change (name, tags, folder, alt text, fit, expiry), which maps cleanly onto the sibling set. It also explicitly distinguishes itself from configure_web_link, which an agent could plausibly confuse with 'change how media plays'. An agent can select this tool 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?

Names the alternative explicitly with the selecting condition: 'For a web link's crop, scroll or refresh use configure_web_link.' It also gives the operative usage rule that this is a partial/merge update ('Only the fields you pass change') so the agent knows not to send a full object. Both the routing decision and the invocation decision are covered.

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