Share

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

The description adds 'end-to-end authenticated' and 'out-of-band pinning' beyond the annotations. Annotations already note the tool is not read-only and not destructive. There is no contradiction, but the description does not detail side effects or concurrency behavior.

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 short sentences with no fluff. The first sentence front-loads the core action and authentication, the second clarifies usage. Every word 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 tool with five parameters (including a nested object) and no output schema, the description covers the essential usage and security requirement. It does not describe return values, but the action is straightforward enough that an agent can infer output.

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?

All five parameters have descriptions in the input schema (100% coverage). The description adds little beyond the schema, only implicitly mentioning cellId and recipient. Baseline 3 is appropriate as the schema already documents semantics.

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 clearly states the verb 'share' with the resource 'a cell' and specifies the action is 'end-to-end authenticated'. It distinguishes the tool from siblings by focusing on granting access, which contrasts with revoke_share, remember, etc.

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?

The description indicates when to use the tool: 'grant another agent access to a specific memory'. It also mentions the prerequisite step 'Pin the grantee's agentIdHash out-of-band'. However, it does not explicitly state when not to use or list alternatives, though sibling tools imply other actions.

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