update_context

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

No annotations exist, so the description carries the full burden for a write tool, yet it never says what mode=replace destroys, whether scope isolates or overwrites prior memory, or whether writes are recoverable. The phrase 'close the gate' is unexplained jargon that implies a hidden state machine the agent cannot reason about.

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 tight sentences with the primary action front-loaded and the lifecycle guidance second. No filler. Minor deduction for the opaque 'close the gate' clause, which spends words without conveying 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?

A five-parameter mutation tool with no annotations, no output schema, and 20% schema coverage needs substantially more explanation than two sentences. Critical semantics — scope addressing, replace vs append behavior, what a session_note is for — are absent everywhere.

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 20% — only session_id is documented in the schema, and the description merely restates that source rather than adding to it. scope, context, session_note, and especially the replace/append enum are given no meaning anywhere; an agent cannot tell whether append concatenates text or merges scopes.

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 and resource: 'Write durable memory or a handoff checkpoint.' This distinguishes it from the read-side sibling get_context and from finish_session, which is named explicitly. It does not differentiate against collapse_context or explain how 'durable memory' differs from a 'handoff checkpoint'.

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?

Gives clear routing: obtain session_id from start_session, and at session end use finish_session instead. That is a genuine when/when-not split. It leaves the choice between durable memory and handoff checkpoint, and between replace and append, entirely to inference.

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