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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. Beyond that, the description is the only source of return-shape information — there is no output schema — and it usefully flags that HTML is only included optionally, which signals payload size can vary.

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 front-loaded sentence with no filler — the substance (what is returned) comes first. It is a verbless fragment, which slightly weakens the opening, but nothing in it is redundant.

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?

With no output schema, the field enumeration carries the return-value burden and does so adequately for a read tool with fully documented parameters and clear safety annotations. Two minor gaps remain: the project_id scoping requirement and the behavior when article_id does not resolve.

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 100%, so every parameter is already documented in the schema, including the size warning on include_html and the default on include_full_analysis. The description only echoes the optional-HTML behavior and adds nothing about project_id scoping or the failure mode for an unknown article_id. Baseline 3 is correct.

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?

It names a specific resource (one article) and enumerates exactly what that record contains — SEO title, meta description, excerpt, key takeaways, stored analysis, publications, optional HTML — which clearly separates it from list_articles. It never explicitly contrasts itself with the sibling, but the 'one article / detail' framing makes the distinction obvious to an agent.

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: an agent infers this is the detail fetch that follows an id from list_articles (the schema note says 'Article id from list_articles'). There is no explicit when-to-use or when-not statement, and no mention of how this relates to score_article or analyze_seo, which also operate on articles.

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