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

With no annotations, the description carries the full burden and does so well: it discloses the role requirement, the visibility of `reason` to refused users, that already-bound graphs remain in place (returned under `already_bound`), and the exact 409 triggers. These are the mutation behaviors an agent needs before invoking.

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 auth scope, then the match_type mechanic, then reason/space_slug, then mutation and error behavior. Sentences are dense but each adds a distinct, call-relevant fact with no filler.

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 permission-sensitive mutation with no annotations and no output schema, it covers what an agent needs: who may call it, how reservation scopes work, the side effects on already-bound graphs, the partial response shape via `already_bound`, and failure codes. Nothing essential 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 must compensate and it does: `match_type` is explained with exact-vs-prefix semantics and a concrete prefix example, `reason` gets its purpose, `space_slug` its delegation behavior, and `iri` its role as the graph IRI or prefix. All four parameters carry meaning beyond the bare schema types.

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 opens with the specific verb+resource ("Reserve a named graph") and the effect ("so other users can't create it"), and the Admin/SuperAdmin qualifier scopes who it is for. It is clearly distinguishable from siblings like brainkb_unreserve_graph and brainkb_list_reserved_graphs.

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 gives clear context for when to use it (preventing other users from creating a graph) and the auth prerequisite, plus the 409 conditions under which it fails. It stops short of naming an explicit alternative tool or a "when not to use" clause, so an agent must infer the routing to unreserve/list on its own.

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