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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds genuine value beyond that: the SSRF-style refusal of local/private/internal addresses and the note that it returns 'response data or errors', which is not derivable from the annotations. It still omits auth handling and timeout behavior.

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 tight sentences with the core action first and the security boundary second. Every clause earns its place; there is no filler or repetition of the name/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?

An output schema exists, so return-value detail is not required, and the description still briefly signals data-or-errors. For a 5-parameter tool with nested objects and no schema descriptions, it is mostly complete for invocation, with timeoutMs and header/auth conventions being the notable omissions.

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 description coverage is 0%, so the description carries the whole burden. It flags variables and headers as optional and constrains the endpoint to public http/https on 80/443, but timeoutMs (default 15000, range 1000-60000) is entirely undocumented and no format or default hints are given for the others. Partial compensation only.

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 (Send) and resource (a GraphQL query) and pinpoints the target scope (public http/https endpoint on port 80/443). No sibling tool performs GraphQL requests, so the agent can identify it immediately without opening the schema.

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?

The description establishes the operational boundary ('public http or https endpoint on port 80 or 443') and an explicit exclusion ('Local, private, and internal addresses are refused'), which implies when it can be used. However, it never names alternatives or states when to prefer this over a sibling like fetch_page_markdown for non-GraphQL HTTP work, leaving routing to inference.

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