Update graph

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

Annotations already declare destructiveHint, idempotentHint and openWorldHint, so the bar is lower, but the description still adds substantive context: making a graph primary changes the default for everyone who has not picked one, only one graph can be primary, unpassed fields are untouched, and it relies on an undocumented web-app API that may change without notice. The user-confirmation requirement is also behaviorally important for a destructive mutation.

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?

Front-loaded with the operation type and the three effects, followed by the constraints that matter. The parenthetical explaining 'primary' earns its length, and the API-instability warning is compact. Minor redundancy between the title-style lead and the 'Only what you pass changes' sentence is negligible.

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?

With an output schema present, return values need no explanation, and the description covers the mutation semantics, id provenance, primary-graph side effects, confirmation gate, and reliability caveat. Slightly incomplete on edge behavior (e.g. whether make_primary=false demotes anything), but nothing essential for a correct call is missing.

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 0%, so the description carries the burden, and it does so well: graph_id must be an exact id from server_info, and the name/description/make_primary parameters map cleanly onto the stated mutations plus the 'only one primary' constraint. It stops short of naming parameters literally, so an agent must still map prose to field names.

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?

Opens with an explicit WRITE: marker and a specific verb+resource pair ('rename a knowledge graph, replace its description, and/or make it the site's primary graph'), enumerating all three mutations. This clearly separates it from create_graph and from the delete/update_semantic_context siblings without needing to open any schema.

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 real usage rules: 'Only what you pass changes' (partial-update semantics), 'graph_id is an exact id from server_info' (routes the agent to server_info to obtain the id), and 'Confirm with the user first' (a prerequisite gate). It does not explicitly contrast with create_graph or state when not to use it, so it falls short of the top band.

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