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

Annotations already declare non-read-only, destructive, idempotent, and closed-world behavior, so the bar is lower. The description adds real value beyond that by disclosing the private visibility scope ("Only you see your saved signals") and by explaining that the destructive-looking operation is actually a reversible toggle via saved=false.

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?

Two short sentences, zero filler, with the core action and its inverse front-loaded and the privacy caveat placed last. Every clause carries 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?

An output schema exists, so return values need no explanation, and the description covers both parameters plus the visibility scope. It is close to complete for a simple two-parameter toggle, with only cross-tool routing left implicit.

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%: signal_id is documented in the schema ("An id from search_signals or what_changed"), but `saved` has no schema description. The description compensates by defining saved=false as the removal switch, covering the undocumented parameter and adding meaning beyond the bare boolean.

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 gives a specific verb+resource (save a signal) and additionally discloses the inverse operation (removal via saved=false), which is more than a restatement of the title. It doesn't explicitly name or distinguish itself from signal-adjacent siblings like pin_signal or rate_signal, so an agent must infer the difference from semantics alone.

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 dual direction (save vs. unsave) is stated, which implies when each mode applies, but there is no explicit guidance about when to use this versus pin_signal or rate_signal, nor any prerequisites. Usage is implied rather than routed.

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