Share

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

Annotations already declare readOnlyHint=false and idempotentHint=false, so the description doesn't need to restate that this is a mutating operation. It adds the sharing-contract framing and clarifies the resource, but it does not disclose outcomes such as response format, whether existing contracts are replaced, or how revocation works. 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 the action front-loaded and the usage guidance immediately after. There is no filler, and the enum repetition is mild enough to keep the description scannable without bloating it.

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?

The tool has five parameters and four required, but the schema fully describes them and the annotations cover the mutation/safety profile. The description supplies the intent and the usage trigger. Remaining gaps—no return-value note and no elaboration on 'syndicate'—are minor and do not prevent correct invocation.

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 100%, so the structured descriptions carry the parameter-level meaning. The description adds relational context by mapping shards to 'specific memories' and repeating the type enum values, but it does not add details like what 'syndicate' means or how expiry interacts with contract type. Baseline 3 is appropriate.

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 uses a concrete verb ('Create') and a specific object ('sharing contract'), then narrows it to 'one or more shards' and granting 'another agent access to specific memories.' This makes the operation unambiguous and distinguishes it from the obvious opposite sibling, saihm_revoke_share.

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 an explicit usage trigger: 'Use this to grant another agent access to specific memories.' This tells an agent when to pick the tool, though it does not explicitly state exclusions or name alternative tools. The sibling list supplies the main contrast with revoke_share.

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