weekly_report

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

The description usefully explains the anomaly of readOnlyHint=false for a reporting tool: it is 'saved as a Markdown file', so the agent understands the write is a local artifact, not a mutation of the site — this is real added value beyond the annotations. It does not disclose where the file lands, what the filename/path convention is, or whether an openWorldHint=true call of this breadth is slow or rate-limited, which are the traits an agent most needs 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?

A single sentence, front-loaded with the payload ('Full report in one call') and followed by an enumerated section list. The parenthetical is long but every item earns its place by telling the agent what questions the report answers, and there is no filler.

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 broad aggregate tool with no output schema, the description is reasonably complete: the agent knows exactly which ten analyses come back and that the deliverable is a Markdown file. Missing pieces are where the file is saved, how to retrieve it later, and how 'days'/'top_n' shape the output, which keeps it below a 5.

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 only 33% — only 'site' is documented — and the description adds nothing about 'days' (the reporting window, 7–90, default 28) or 'top_n' (3–50, default 10). Given that 'top_n' clearly governs how many rows appear in each section and the description lists ten sections that will be truncated by it, this is a meaningful gap the description should have closed.

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 description names the resource ('full report') and enumerates its ten sections (performance, alerts, drops, quick wins, content gaps, decay, cannibalisation, sitemaps, indexing, robots.txt), which implicitly distinguishes it from the granular siblings like performance_query, check_alerts, and content_decay. The verb is only implied ('in one call ... saved as a Markdown file') rather than stated outright, and the tool never says what data source it operates on, so it stops short of a 5.

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?

'Full report in one call' hints that this is the aggregate alternative to calling many section tools individually, which is useful routing signal. However, there is no explicit 'use this when...' statement, no mention of when a narrower sibling like section_performance or find_opportunities would be preferable, and no cost/latency caveat for an agent deciding between one broad call and several focused ones.

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