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

readOnlyHint: true already covers the safety profile; on top of it the description adds the "GET only" method restriction and the raw-passthrough nature. It omits behavior on errors, rate limits, and response passthrough, but with the annotation handling the critical read-only trait this is adequate, not rich. No contradiction.

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 purpose front-loaded; the examples compress a lot of meaning into few words. The redundant "READ-ONLY" label duplicates the annotation slightly, but the text is otherwise all signal and correctly ordered: purpose, then constraints, then mechanics.

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-param raw-passthrough tool with a read-only annotation and no output schema, the description covers what, when-not, and safety. Documenting return values would be near-meaningless for arbitrary unwrapped paths since output is whatever the Sendbird API returns, so that gap is acceptable. Minor omission: error or rate-limit behavior, low-value for an escape hatch.

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% with detailed, well-exampled descriptions for both path (including a URL-encoding example) and params. The description's "Platform API: GET {path}" merely echoes that, adding no semantic value beyond the schema. Baseline 3 applies.

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 ("issue a raw GET") against a specific resource class ("any Chat Platform API v3 path not wrapped by a dedicated tool") and positions itself as a power-user escape hatch. The concrete examples (/report, /applications/settings_global) make the scope unmistakable and separate it from the dedicated sibling tools.

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?

"Not wrapped by a dedicated tool" is an explicit when-not condition that steers the agent to siblings when they cover the path, and "Power-user escape hatch" signals fallback status. It does not name specific sibling alternatives or phrase the preference directive, but the exclusion is clear enough.

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