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

Annotations only declare the safety profile (readOnlyHint=false, openWorldHint=false, destructiveHint=false), and the description adds substantial behavior beyond them: the api:chat scope requirement with a 403 failure mode, per-turn token quota consumption, 1-2 minute latency, server-side conversation persistence across calls, and one-thread-per-Gambit semantics. These are exactly the operational facts an agent cannot infer from annotations or schema.

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 correctly: purpose, then auth, then cost/latency warning, then threading rules, then the image workflow and siblings. Every sentence carries information, but the single semicolon-heavy block is dense and the image-upload clause could be split or deferred for easier scanning.

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?

Complete for a mutation-adjacent, non-idempotent tool with no output schema: it covers auth prerequisites, cost, latency, state persistence, thread identity, and the prerequisite upload step for images. Nothing an agent needs in order to call it correctly or avoid misuse is missing.

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 75%, but the description still adds real meaning: case_id is sourced from list_gambits (the schema says only 'a Gambit id from list_gambits') and is shown to route to the same thread the user sees in the app, while being mutually exclusive with new_conversation. image_urls is explained as an upload-first workflow via POST /api/chat/images with accepted formats and a 24-image cap, which the schema does not convey.

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 (talk to your Gambit trading agent) plus the exact scope of what can be discussed: market takes, position analysis, recommendations, strategy. It is explicitly distinguishable from the sibling read tools it names (list_conversations, get_conversation, manage_conversation) and from execution tools, since it declares 'this channel cannot execute trades or move funds.'

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?

Explicit when-to-call and when-not-to-call guidance: 'don't call it speculatively' because each turn is a real run costing 1-2 minutes and AI tokens. It also gives the routing rule for case_id versus starting a new thread, states the mutual exclusion between case_id and new_conversation, and redirects history management to the three sibling conversation tools.

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