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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's added value is in the specifics: portal wording and attribution are immutable, and capture identity, review decisions and linked tasks stay unchanged. It also explains merge semantics (omitted fields preserved, empty string clears optional fields), which is a genuine behavioral disclosure. It stops short of explaining what makes the call 'destructive' or whether clearing a field is reversible.

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?

Three tight sentences, front-loaded with the mutable field set and followed by immutability and merge rules. Every sentence earns its place; the only blemish is the overloaded word 'context', which costs a little clarity.

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 destructive, open-world mutation with 10 parameters, no output schema and only 40% schema coverage, the description covers most of what an agent needs: which fields are editable, which are preserved, and how to clear optional values. Remaining gaps are the required `context` analytics parameter contract and the absence of error/permission behavior.

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?

With 40% schema coverage across 10 parameters, the description does useful work by mapping editable fields to schema properties (type, areaId, hiddenFromPortal, title, submitterName, sourceLabel). But the word 'context' is ambiguous between the required analytics `context` parameter and the signal's content/description field, and projectId, signalId and the required `context` contract are never addressed.

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 (update) and resource (signal), then enumerates the mutable facets: type, area, portal visibility, title, context, reporter, reference. It also carves out what is out of scope (portal wording, attribution), which helps separate it from signals_capture or signals_delete without naming them.

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?

Use is implied by the phrase 'correct a manual signal's title, context, reporter or reference', which signals a correction workflow rather than creation. However, no sibling alternatives are named (e.g., signals_capture for new signals, signals_dismiss for status), and there is no explicit when-not guidance.

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