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

Adds genuinely non-obvious behavior beyond the annotations: the call consumes an AI credit, which is a cost signal no structured field carries, and it clarifies the advisor can read live account objects. 'It is read-only' merely restates readOnlyHint=true (consistent, not contradictory), and latency or answer format is not disclosed, so it falls short of a 5.

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?

Four sentences, front-loaded with purpose, then capability scope, then usage cues, then cost/caveat. Every sentence carries distinct information and the cheaper-alternative warning lands last where an agent will still read it.

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 2-parameter tool with no output schema, the description covers capability scope, cost, safety, and alternatives adequately. It does not indicate what the response looks like (prose answer vs. structured data) or how long it may take, which matters for an AI-backed 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 only 50% (the `question` param has no description), so the description compensates by specifying 'plain English' and 'one self-contained question' — a real constraint telling the agent not to send follow-ups or rely on prior turns. The 2000-character cap and the project-scoping behavior are left to the schema.

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 the fnlowl Advisor a question in plain English') and then enumerates the exact knowledge domains the advisor covers (widgets, embed, sequences, campaigns, sending, credits, plans, MCP) plus the account data it can read. This distinguishes it clearly from the read_* and list_* siblings, which it explicitly references.

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 concrete example phrasings ('how does X work', 'why is Y empty', 'what should I do next') that define the intended use class, and names the alternative with the selecting condition: 'a direct read tool is cheaper when the data needed is already known.' Both when-to-use and when-not-to-use are present.

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