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

Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description supplies the missing 'why' by explaining that the write behavior is limited to adding a share from a link and that everything else is a read. It also discloses a non-obvious side effect of a sibling (unfiltered memory_search surfaces share content, labelled). It doesn't describe what the listing returns or how shares can be revoked.

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 routing and accept instructions are front-loaded and compact, but the embedded "Pavel shared Substrate - summary with you" sentence reads as sample data rather than definitional content and risks confusion. Removing it would lose nothing and tighten the definition.

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 single-optional-parameter tool with full schema coverage and no output schema, the description covers the important bases: what a share is, how to consume one elsewhere, and how to add one here. The main omission is any hint of what the listing yields (count, titles, metadata) or whether accepting is idempotent on repeat calls.

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% and the `accept` property already documents the token and its format, so the schema does the heavy lifting. The description repeats where to find the token (after share= or /s/) rather than adding new meaning such as what happens on an invalid or already-accepted token. 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 states the resource precisely ("Shares other people gave you") and distinguishes it from the search siblings by explaining that shares are read via the `share` argument of memory_search/expand/evidence. The listing verb itself is only implied by the noun phrase and the title, and the sentence "Pavel shared Substrate - summary with you" is a leaked example that briefly muddies what the tool actually does.

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?

Explicit guidance is given for both paths: read shares through the `share` argument of memory_search, memory_expand and memory_evidence, and add a share by calling this tool with `accept` set to the link token. It even notes that plain memory_search returns best matches labelled, which helps the agent decide which route to take. It stops short of an explicit "call memory_shares first when you don't know what was shared" rule, but the routing context is strong.

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