Grant Add

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

With no annotations the description carries the full burden and does disclose real behavioral traits: over-broad keywords such as 'yes' or 'go' are refused, certain scopes are rejected outright, and id auto-defaults to the next G<n>. It does not say what happens on conflict with an existing grant or what the call returns, but the rejection and defaulting rules are substantial beyond the schema.

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?

The main action is front-loaded, but the body is a run-on with parentheticals and line breaks mid-sentence, making it harder to scan than it needs to be. Most content earns its place, but the compression into a single paragraph-per-field style costs readability.

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?

An output schema exists so return values need not be described, and the description covers the required parameters, their formats, and the rejection rules. Remaining gaps are the unexplained date and topic parameters and no statement about duplicate-grant behavior, which is a modest shortfall for a mutation tool without annotations.

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 0%, so the description must compensate and largely does, giving accepted source formats ('D-150', 'hq:D-150', 'n5737', 'vr:<scene>:<id>', 'chat: ...', 'memory: <name>'), the keyword matching rule with examples, and the owner requirement for routes. Two of the eight parameters, date and topic, are never explained in either field.

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 a specific verb and resource ("Record a standing grant ... or a route") and defines the two record kinds and their differing semantics (owner acts without asking vs asks routed to an agent). That clearly separates it from grant_check/grant_list/grant_drop, which are read/inspect siblings, though the prose is dense enough to require careful reading.

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?

States the triggering condition ("the person said yes to a kind of step") and the two modes with their selection rule (kind='grant' vs kind='route', owner required for route). It also gives the exclusion rule that public, money, accounts and deleting cannot be granted, which is exactly the when-not guidance an agent needs.

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