page_metadata

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, but the description adds nothing behavioral beyond that: no indication that it performs a live network fetch, how failures or unreachable pages surface, or whether credits are consumed. The listed fields are output content, and an output schema already exists, so they earn no transparency credit here.

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?

It is a single short sentence-fragment with no padding, but it is under-specified rather than concise: the most important part (what the tool does) is absent while returned-field names, already exposed by the output schema, occupy the whole line.

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 one-parameter fetch-and-extract tool in a crowded SEO sibling group, the definition omits the core action, the usage boundary against seo_audit/compare_seo, and any note about the live fetch or credit cost, even though the output schema and annotations relieve it of documenting returns and safety.

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?

With one required parameter and 0% schema description coverage, the description should clarify what 'url' accepts (absolute vs relative, scheme required, redirects), but it says nothing about it. The single obvious parameter keeps the gap small, so this sits at minimum-viable rather than failing.

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?

The text is a bare noun list of data categories ('Title, description, canonical, lang, robots, Open Graph, JSON-LD types, H1-H3 and image alt stats') with no verb, so the agent must infer that the tool fetches a page and extracts metadata. The field list does hint at SEO-oriented extraction, which partially separates it from read_url and extract_links, but it never states the action or the resource explicitly.

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?

There is no when-to-use guidance at all, despite close siblings (read_url, seo_audit, compare_seo) where routing matters. Nothing says whether this is a single-page inspection step before seo_audit or an alternative to it, and no prerequisites or exclusions are given.

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