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

Annotations only declare readOnlyHint/ destructiveHint / openWorldHint, so the description is doing real work by disclosing the mechanism: a link opens the Komers sign-in and consent screen, the owner sees what will be shared and must choose Allow. That is important behavioural context an agent would otherwise lack. It stops short of saying whether the tool returns a URL versus redirecting, how long the link lives, or what happens if an account is already connected — but the consent flow itself is well disclosed. There is mild tension with readOnlyHint=true, since an account connection is persistent, though the description makes clear the mutation happens in-browser at owner consent rather than at the tool call.

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 sentence is front-loaded with the action ("Connect the owner's Komers account...") and the parenthetical enumerating shared data earns its place by telling the agent what becomes accessible. It is dense — two follow-on tool names bundled into one sentence — but there is no filler and no repetition of the title.

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 one-optional-parameter tool with no output schema, the description covers what it does, the consent mechanics, and the downstream tools it unlocks. The remaining omissions — return value (link vs. redirect), link expiry, and the already-connected case — are minor but would be useful for a tool whose whole purpose is producing an authorization handoff.

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?

There is a single optional parameter, `site`, and its schema description ("the site to return to after connecting") already covers it at 100% coverage. The tool description adds no further meaning about the parameter, which is acceptable given the schema does the work, but nothing is gained either.

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 opens with a specific verb and resource: connecting the owner's Komers account (explicitly listing the data that lives there: products, orders, customers, bookings, chats) to Komers Sites. It also distinguishes the action from its nearby siblings by naming komers_tools, komers_call and set_site_komers_store as the follow-on steps, so an agent can place this tool in the account-linking family rather than the store-linking one.

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?

Usage is implied clearly: this is the prerequisite step that must happen before komers_tools / komers_call work and before set_site_komers_store can pick a selling store. What is missing is explicit guidance on the negative case — whether to call komers_status first, and to use disconnect_komers to revoke — but the sequencing context is strong enough that an agent knows when to reach for this over a sibling.

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