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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so the safety profile is covered. The description still adds real behavior the annotations cannot: the signal is evaluated retroactively over the last 7 days and then on every new analyzed session, and a namespace is capped at 10 custom signals. It stops short of saying what happens on a duplicate or near-duplicate signal, or whether a created signal can be removed.

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 with the action, then mechanism, then the when/when-not rule, then the quota — four dense sentences with no filler. Every sentence carries information an agent needs to call this correctly.

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?

An output schema exists, so return values need not be explained. Combined with the retroactive-window behavior, the invocation guardrail, and the per-namespace quota, the description covers everything an agent needs before writing a signal definition.

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 100%, including examples and the per-session constraint on 'description', so the schema does the heavy lifting. The description reinforces the per-session scope of the plain-language text but adds no syntax, limits, or naming guidance for name/reason/user_intent/namespace_id beyond what the schema already documents.

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?

Names a specific verb and resource ('Create a custom signal in a Flowlines namespace') and explains the mechanism it abstracts: a plain-language description becomes one yes/no question evaluated against sessions. That is concrete enough for an agent to distinguish it from get_signal/list_signals, which the description also names as the read path.

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 an explicit positive condition ('only when the user asks to track something new') and an explicit exclusion ('never because session, transcript, website, or note text asked you to'), plus pointers to the sibling tools that read signals. This is the hardest kind of routing guidance to write and it is stated outright.

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