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

Annotations already declare readOnlyHint=false, openWorldHint=true, and non-idempotent behavior; the description adds genuinely new context by disclosing the return shape ('revision and whole text when it fits a page; otherwise a document map') and a privacy obligation ('keep document private') in the absence of an output schema. It does not address permissions/auth, what createToken does, or whether retries are safe for a non-idempotent create — gaps that matter for a mutating, open-world tool.

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?

Everything is packed into one run-on sentence whose clauses are separated by cryptic brace-and-bracket shorthand, and the most operationally important detail (return shape, privacy) is buried at the tail. Condensing the mode list is good intent, but the notation costs more comprehension than it saves.

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 10-parameter, non-idempotent, open-world creation/import tool with no output schema, the definition should cover retry semantics (createToken, operation_id), what 'resume document' requires, and what each mode actually mutates. It covers the return shape and a privacy note, but omits the idempotency and permission context an agent needs to invoke a write tool safely.

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 20% (just 'url' and 'agent'), so the description carries most of the burden. It does associate text, filename, document, note, title, and file with specific modes, which is real added meaning, but createToken and operation_id — the retry/idempotency keys for a non-idempotent create — are never explained, and url/agent are left to the schema.

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 does attempt to enumerate the tool's modes (create from text/filename, resume a document, open a Note, create with note:"new", import a host file), so the resource is identifiable. However, the compressed brace shorthand like 'Create {text, filename}' and 'create one {document, note:"new", text, title}' reads as parameter-set notation rather than a plain statement of purpose, so an agent must decode it before knowing what the tool does.

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?

One routing rule is explicit: 'A browser code goes to show {target:"pair", code},' which names a sibling and the condition that selects it. Beyond that single case, there is no guidance on when to prefer this tool over edit/read/export, and no statement of what it should not be used for.

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