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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the write-once nature is covered. The description adds genuinely new behavioral context beyond that: the call consumes metered points scaled by model, and the answer is not returned inline but must be fetched via get_deep_thread. It omits any detail on what the immediate response contains or partial-failure behavior.

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?

Front-loaded purpose is good and the whole thing is short, but 'Uses points' is immediately restated by the parenthetical '(uses points, metered on the models used like the website)' — pure redundancy. Trimming that would make it tighter without losing information.

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?

With no output schema, the description partially compensates by telling the agent answers come from get_deep_thread, which is the key missing return-value fact. However it says nothing about what the immediate call returns, authentication/point-balance prerequisites, or failure modes, leaving real gaps for a metered, mutating call.

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 67% and the description supplies essentially no parameter-level information. 'message' has no schema description and the description never clarifies it is the follow-up question; 'analysis_id' and 'mentions' are already documented in the schema, so the description adds nothing for them. The 2000-char message limit and the 3-seat mentions cap go unexplained.

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: 'Ask a follow-up question about a finished deep research run.' The word 'finished' implicitly separates it from start_deep_analysis, and pointing at get_deep_thread distinguishes the asking action from the reading action. It stops short of explicitly naming which sibling to use instead when the run is not finished.

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 clear prerequisite ('a finished deep research run') and routes the agent to the alternative for retrieving results ('read the answers with get_deep_thread'). No explicit when-not-to-use or error-condition guidance, so it lands just below the top tier.

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