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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds meaningful context beyond them: that returned content is 'public metadata and body paragraphs' and that the response includes 'the upstream's own restricted-access signals', warning the agent that paywalled/gated content may be signalled rather than fully returned.

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?

A single dense sentence with the resource and scope front-loaded and no filler. It could be marginally clearer, but no sentence is wasted.

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 values need not be enumerated here. For a one-parameter read tool the description covers what comes back (metadata, body paragraphs, access signals), leaving only edge-case behavior (partial content on paywalled articles) unstated.

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?

The single parameter has a plain 'string' schema with 0% description coverage, so the description must carry the burden. It partially compensates by specifying 'canonical article URL', implying the expected format, but gives no example or note on what makes a URL valid/acceptable.

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+resource: retrieves one SCMP article's public metadata and body paragraphs from a canonical article URL. This clearly distinguishes it from sibling list tools (scmp_headlines, scmp_sections) by scoping to a single article, though it does not name a sibling explicitly to sharpen the contrast.

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 only implied: 'from a canonical article URL' hints that the input must be a full canonical URL rather than an ID or slug, which is useful, but there is no explicit when-to-use/when-not guidance or pointer to alternatives like scmp_headlines for discovery.

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