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

Annotations already indicate readOnlyHint=false and destructiveHint=false, and the description aligns by describing a mutation. The description adds valuable context beyond annotations: it specifies the fields affected, the ownership requirement ('принадлежащей клиенту'), the editability constraint, and the lack of submission side effect. This is substantive additional behavioral disclosure, though it does not detail error cases or reversal.

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?

The description is two concise sentences with no redundant words. It front-loads the action and scope, then adds the key non-submission behavior. Every sentence earns its place, making it highly efficient.

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?

While the output schema and annotations cover some aspects, the description leaves notable gaps: it does not explain the purpose of the required idempotency_key, what 'editable' means or what happens if the link is not editable, and whether the update is partial or full. Given the tool's complexity (6 params, 2 required), the description is too brief to be fully complete on its own.

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 0%, so the description must compensate. It names four of six parameters (url, anchor, context_text, scheduled_at) via 'URL, анкор, окружающий текст или дату', but fails to explain the required parameters link_id and idempotency_key. The idempotency_key, which is mandatory and critical for idempotent behavior, receives no mention, leaving a significant gap for agents to invoke the tool correctly.

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 clearly states the verb 'меняет' (changes) and the resource (link), and enumerates the specific fields that can be updated (URL, anchor, context text, date). It also distinguishes itself from siblings by noting 'не отправляет задачу в работу' (does not send the task to work), differentiating it from submit_link and other workflow tools.

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?

The description provides clear context for when to use the tool: 'пока она редактируема' (while it is editable) and 'не отправляет задачу в работу' (does not send the task to work). This implies it is for editing drafts before submission, contrasting with submit_link. However, it does not explicitly name alternatives or list when not to use it, so it falls slightly short of a 5.

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