sync_sessions

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal that preview is the default behavior, that applying is refused while the desktop app runs, and that a plan is returned either way. It does not explain what the plan contains or any side effects of applying (e.g., permanent changes to session data). The description gives a moderate level of transparency but omits important details about the impact of applying changes.

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 concise, consisting of two sentences that front-load the primary purpose (preview or apply a sync). It efficiently covers the default behavior and the main constraint about the desktop app. There is no wasted text, and the structure is clear. However, it could be slightly more structured by separating the parameter explanation into a list, but it remains effective.

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?

Given the tool has 3 parameters, no output schema, and no annotations, the description should be comprehensive. It explains the purpose, the default mode, and the refusal condition, and gives format for accounts. It does not describe the return value beyond 'the plan is returned', nor does it explain the semantics of keep_deleted or apply_changes. The description is adequate for a basic understanding but leaves out details that an agent might need for correct invocation, especially regarding parameter behavior and expected output.

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 explain all parameters. It only explains the 'accounts' parameter, specifying that it should be two uuid prefixes separated by a comma when more than two accounts exist. It does not explain 'keep_deleted' or 'apply_changes' beyond their names. The name 'apply_changes' is somewhat self-explanatory, but 'keep_deleted' is ambiguous. The description adds value for accounts but fails to cover the other parameters, which is a significant gap given zero schema coverage.

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 states a specific action (preview or apply a sync) on a specific resource (sessions between two accounts). It clearly distinguishes between preview and apply modes, which is central to the tool's purpose. It does not explicitly differentiate from sibling tools, but the siblings (list_accounts, find_sessions, terminal_only_sessions) have obviously different purposes, so the purpose is clear enough.

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 gives some usage context: it explains when to specify the accounts parameter (when more than two accounts exist) and notes that applying is refused while the desktop app runs. However, it does not explicitly say when to use this tool versus alternatives, nor does it provide any 'when not to use' guidance. The advice about the desktop app is useful but the overall guidance is incomplete.

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