start_memory_save_interview

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

With no annotations, the description carries the full burden, and it does disclose two important behaviors: the exact-phrase precondition and that starting the interview is not itself a save. It says nothing about auth/consent state (owner_token), side effects of starting, or what the interview produces.

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 short sentences with the core precondition front-loaded and the disambiguation note last; every sentence carries information. Slightly dense formatting with the embedded quoted phrase, but no waste.

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 stateful, multi-step consent flow with no annotations and no output schema, the description covers the entry gate but omits the follow-on flow, required identity inputs, and result semantics. Adequate to decide whether to call, incomplete for calling it correctly.

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% across 4 parameters. The description only hints at the value of trigger_phrase (the exact Russian phrase) without mapping it to the parameter, and says nothing about profile, owner_token, or candidate_text, so it fails to compensate for the coverage gap.

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 ("Start the mandatory consent interview") and distinguishes itself from the save operation with "Starting an interview does NOT save a memory," which routes the agent away from save_memory. It does not name siblings explicitly, but the negation effectively separates it.

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?

Gives a concrete gating condition: the tool only succeeds if the user said the exact phrase "Сохрани воспоминания в архив," which is real when-to-use guidance. It lacks any statement of what to do instead when the precondition fails (e.g., point to save_memory or decline).

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