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

Annotations declare destructiveHint=true, and the description complements that by explaining the durable shared-brief effect and giving exact merge vs replace semantics ('upserts the keys you pass and leaves others intact' vs 'overwrites the entire facts object'). It also preempts a futile search for a link tool by saying links come from the Tango UI. No contradiction with annotations.

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?

Purpose is front-loaded in the first sentence, usage guidance follows, and the facts_mode semantics are set off as a clear final block. Every sentence earns its place, including the note about reference links and read-only alternatives.

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 5-parameter tool with no output schema, the description covers the main call decisions: when to use, merge vs replace, and where to get links. It doesn't explicitly spell out that client or client_id must be supplied, and it is silent on return values, though the schema covers the client identifier options.

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 80%, so the schema already does most parameter documentation. The description adds real value by explaining facts_mode behavior and framing facts as durable ground-truth, but client, client_id, and brief_md semantics are left to the schema.

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?

Description opens with 'Write or revise the shared brief and structured facts for a client', a specific verb+resource statement. It also distinguishes itself from log_client_decision for one-off learnings and from read-only context-source tools, so an agent can tell siblings apart.

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?

It says when to use ('after an intake conversation, discovery call, or whenever you learn durable ground-truth about the client') and explicitly routes one-off decisions/learnings to log_client_decision and external-system reads to list_context_sources / query_context_source. That is clear context with exclusions.

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