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

Beyond the annotations (which only flag it as a non-readonly, open-world, non-idempotent, non-destructive write), the description discloses key hidden behavior: the link expires after 14 days, the client consents themselves after seeing who is asking, and crucially that creating the link does NOT attach any account automatically. That deferred-effect caveat is exactly the kind of context annotations cannot convey.

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?

Front-loaded with the core action in the first clause, and the length is justified by the multi-step workflow it explains. A couple of sentences (the client-opens-it narrative) lean descriptive rather than directive, which keeps it from a perfect 5.

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 no output schema and only skeletal annotations, the description covers purpose, lifetime, consent flow, and the important post-creation behavior (accounts appear in list tools tagged with the client login). It never states what the call itself returns (the URL/token/identifier), which an agent acting on the result would want.

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 baseline is 3, but the description goes further by expanding the opaque enum values into real-world meaning (google = Analytics/Search Console/Ads login, meta, business_profile, crm, wordpress) and by clarifying that 'client' is the name the agency uses. This makes the platforms parameter more interpretable than the schema alone.

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?

States a specific verb and resource ('Create a link') and immediately scopes who it is for and what it enables (an agency sending a link to a client so the client connects their own accounts). It is clearly distinguishable from siblings like connect_platform and link_account, which operate on accounts, not on a shareable invitation.

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?

Explains the situation that selects this tool: use it when you want the client to connect their own accounts 'instead of granting the agency manager access.' That is a real when-to-use condition. It does not, however, name the alternative sibling tools (e.g. connect_platform or link_account) or state exclusions, so it falls short of a 5.

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