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

With no annotations, the description transparently reveals the side-effect: it 'SHOWS THEM A CARD to approve' but does not connect or grant access. It also states the answer belongs to the owner, setting expectations. The description fully carries the behavioral burden; no annotation contradiction exists.

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 description is front-loaded with the purpose and immediately clarifies the non-connect behavior. While multi-sentence, each sentence adds necessary nuance (card, no connection, no repetition, alternative scenario). It is comprehensive without redundancy, though it could be slightly tightened.

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 2-parameter tool with no output schema, the description covers when to invoke, what happens (card shown, no access), user communication after calling, common misuse (repeated calls), and a frequent confusion (already connected but no access). Nothing an agent needs to call it correctly is missing.

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 schema already provides detailed descriptions for both parameters (e.g., reason with concrete examples, toolkit_slug with allowed values and refusal conditions). The tool description adds no new parameter-specific guidance beyond what the schema gives, so the 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 clearly states the verb 'Ask your owner to connect', the resource 'third-party app', and immediately clarifies the crucial nuance: it 'does NOT connect anything and does NOT give you access'. This single tool is distinctly about requesting a connection, not performing it, and examples (Gmail, Slack, Notion) make the scope obvious.

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?

Provides explicit when-to-use ('Call it when a task needs an app you cannot currently reach'), what to do after ('tell the user plainly that you have asked'), and what to avoid ('Do not call it repeatedly for the same app in one conversation'). It also differentiates an alternative scenario (app already connected but no access) and directs the user to Settings, giving a complete decision tree.

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