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

Annotations already declare non-readonly, non-destructive, non-idempotent. The description adds real behavioral context: changes take effect immediately, no publishing/versioning required, images are size- and dimension-capped, null clears an image, and language affects lang/dir and OG locale. Missing only permission/auth requirements.

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?

Dense but front-loaded, leading with the core action and effect. Every clause carries information (constraints, semantics, alternatives), though the third clause is somewhat compressed and reads abruptly.

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 7-parameter mutation tool with no output schema and low schema coverage, the description covers the highest-risk parameters but omits name/description semantics and any auth/permission context. Adequate but with visible gaps.

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 only 29%, so the description must compensate, and it partially does: it documents social_image/icon format, 5 MB / 4096px limits, and null-clears behavior, plus language semantics. However, name, description, and app_id receive no description-level explanation, leaving several params undocumented in both places.

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 ('Update public HTML-shell metadata') and scopes it as immediate, distinguishing it implicitly from update_app, update_entity_metadata, and write_app_file. It is clear what the tool does, though it does not explicitly name a sibling it replaces.

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?

'without AI, code edits, publishing or Saved Versions' tells the agent when this is the lightweight path versus publish_app/write_app_file, and the seo.json note routes per-page card work elsewhere. No explicit 'do not use this when...' clause, but the context is strong.

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