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

Annotations already declare readOnlyHint=false and destructiveHint=true, which is a strong signal. The description adds critical context beyond that: the destructive nature of facts_mode='replace' (overwrites entire facts object), the 'merge' default behavior, and the note about links being UI-only. One gap: it doesn't spell out that brief_md clearing requires empty string/null, though the schema covers this.

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?

Well-front-loaded: purpose, usage triggers, sibling routing, then behavioral specifics. The trailing facts_mode and API reference are useful but could be tightened. Overall no wasted sentences, though slightly dense.

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?

No output schema, but the tool is a mutation where return values matter less. The description covers triggers, sibling routing, facts_mode danger, and the UI-only link situation, all necessary for correct invocation. Minor omission: explicitly warning that 'replace' is irreversible.

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 80%, so many params are documented. The description nonetheless adds real value: it explains facts_mode semantics (merge upserts, replace overwrites) beyond the schema's brief enum description, and cites the precedence/disambiguation rule for brief_md. It also documents the absence of a link parameter, which is important given 'Reference links' is mentioned but has no corresponding schema field.

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?

Specific verb+resource combination: 'Write or revise the shared brief and structured facts for a client.' It explicitly distinguishes itself from siblings (log_client_decision, list_context_sources, query_context_source) and states the inheritance consequence for future agents/humans.

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?

Explicit trigger conditions ('after an intake conversation, discovery call, or whenever you learn durable ground-truth') and a named alternative for the disambiguation case ('For one-off decisions/learnings, prefer log_client_decision'). Sibling routing is complete.

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