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

Annotations declare readOnlyHint=false and destructiveHint=false; the description corroborates this by explicitly saying the fact is 'kept in the record (never deleted)' and only removed from the working set, which is valuable non-obvious behavior. It does not cover auth/permission requirements or what the response contains.

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 action and its key behavioral consequence. The trailing API reference link is mildly extraneous but harmless.

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 6-parameter mutation with no output schema, the behavioral intent is well covered, but the description omits how the fact is located (client vs client_id vs project_id overlap) and whether anything is returned on success.

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 83%, so the schema already documents key, reason, client, project_id, and superseded_by. The description adds context on the reason and the replacement key but says nothing about how client / client_id / project_id select the fact scope, leaving overlapping parameters undifferentiated.

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 ('Mark ... as no longer true') and resource ('one client or project fact'), and the phrase 'drops out of the working set every agent reads' pins down the semantics precisely, distinguishing it from sibling mutators like update_client_context or confirm_context_fact.

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 makes the usage condition clear (a fact that is out of date) and instructs the agent to supply a reason and an optional replacement via superseded_by. It implies contrast with deletion ('never deleted') but does not explicitly name an alternative sibling or state when not to use this tool.

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