agent_grant

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

With no annotations, the description carries the full burden for a mutation tool. It does not disclose required permissions, whether the grant is idempotent or revocable, what happens to existing grants, or the effect of the 'access' field. Worse, it says '读取' (read) while the schema permits write, leaving the actual behavioral scope of the grant unclear.

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?

A single compact sentence front-loads the action and the resource/direction, with no wasted text. It is efficient, though its brevity is as much under-specification as concision.

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 mutation tool with no annotations, no output schema, and 0% parameter coverage, the description should explain the access parameter, permission requirements, and reversibility. It omits all of these and its read-only phrasing conflicts with the write option, so it is not complete enough to invoke confidently.

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 should compensate for all three parameters. It clarifies that owner_agent supplies the memory and principal is the receiving agent or team:id, but leaves 'access' (read vs write enum) entirely undefined and omits format details for the identifiers.

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 (grant/authorize) and resource (an agent's private memory) plus the direction of access. It is clearly a permissions-granting tool, distinguishable from the memory_* and event_* siblings by its authorization framing. It stops short of naming which sibling it complements (agent_recall/agent_remember), but the core purpose is unambiguous.

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?

There is no guidance on when to use this versus memory_search, memory_add, or agent_recall, nor any prerequisites, exclusions, or the conditions under which a grant is appropriate. The agent must infer the entire usage context from the one-line purpose.

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