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

Annotations only state readOnlyHint=false and destructiveHint=false, so the description carries the behavioral load. It adds non-obvious behavior: partial-update semantics (not full replacement), that attributes must be pre-registry ids (not arbitrary values), and that the Space binding affects which entity gets written. These are material behavioral facts that annotations do not provide. 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?

Two sentences with zero filler. The action and scope are front-loaded ('Partially update a concept'), and the second sentence delivers the scoping caveat plus two resolution paths (set_active_space or space_id) in highly compact prose. Nothing extraneous earns its place.

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 mutating tool with no output schema, the description covers the essential decision inputs: which fields change, the partial-update nature, and the potentially surprising Space-scoping behavior that affects which Space gets changed. It doesn't describe return values or failure conditions (e.g., nonexistent concept id), but the guidance is enough to reliably invoke the tool.

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 67% and the description compensates meaningfully: it clarifies that 'attributes' takes only registry ids, that 'name' is one of the updatable fields, and that space_id functions as a one-call override of the session's active Space. The unused concept_id is left without description in both schema and description, but its role is fairly obvious for an update-by-id tool.

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?

The description names a specific verb (update), resource (concept), and explicitly scopes the fields — 'name, attributes — registry ids only.' This clearly distinguishes it from the many other update_* tools (update_asset, update_angle, etc.) and from the create/delete/get_concept alternatives.

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 provides important contextual guidance: the operation is scoped to the active Space, tells the agent exactly how to switch (set_active_space) or how to override per-call (space_id). This is genuinely directional context for correct usage. However, it does not explicitly rule out when not to use it (e.g., 'use create for new concepts'), leaving some inference to the agent.

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