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

Without annotations, the description carries the full burden and succeeds: it discloses idempotent upsert behavior, edge-triggered one-shot, re-arm conditions, TTL auto-expiry, and that no quote is run for the target kind. It also notes the FREE key requirement and SSE streaming endpoint outside MCP.

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 dense but each clause adds necessary detail for a complex 14-parameter tool. It is front-loaded with the core action and then elaborates. While long, it avoids redundancy and stays structured.

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 tool with no annotations and many parameters, the description covers the operation, both kinds, parameters, lifecycle (re-arm, TTL), and how to consume events (SSE vs polling). This is sufficient for an agent to invoke it correctly, especially with an output schema present.

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 0%, so the description must compensate. It names most relevant parameters grouped by kind: asset_id, op, threshold_usd_micro for price; amount_in, asset_in, asset_out, min_out, margin_bps for target; plus client_key, rearm_bps, cooldown_s, ttl_s. It omits explicit mapping of api_key (though 'needs a key' implies it) and doesn't enumerate default values for all params, but the coverage is strong.

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 opens with 'Register a standing server-side watch' and then details two kinds (price/target), making the operation clear. It distinguishes from siblings by stating that fires are hints and that get_quote should be used for re-quoting, and list_watches for MCP polling. This is a specific verb+resource with clear scope.

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 explains when to use the tool (to set up standing watches) and contrasts with get_quote ('Fires are numbers-only HINTS: re-quote with get_quote') and list_watches ('from MCP, poll list_watches'). It does not explicitly state exclusions (e.g., 'use get_quote for immediate quotes') but implies them through the hint/re-quote guidance.

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