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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is scope and side effects, and it delivers: reading never triggers a run, the report covers only the first 500 sitemap URLs, up to 3 competitors, and is tied to a watch-package entitlement ('one site for every 25 paid pages'). Those are non-obvious operational constraints not derivable from the schema or annotations.

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?

The opening sentence front-loads the payload well, but the final sentence repeats 'Reading never runs the report' verbatim from the second sentence — a pure duplication of roughly a third of the text. The middle sentence also packs cadence, URL cap, change types and competitor limits into a single dense clause rather than separating scope from entitlement.

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 description carries the return-shape burden and does so at a high level: change summary, new/fixed problems, new pages, competitor new pages. Together with the entitlement note and the no-run guarantee, an agent has enough to call it correctly; only the empty-state behavior (no report yet) is left unaddressed.

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% and the two parameters are already documented (site id, optional lang for Portuguese texts), so the baseline applies. The description adds no meaning about the id parameter — notably it does not say what happens if the site is not on a watch package or has no report yet, which is the main semantic risk for this tool.

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 first sentence states a specific verb and resource ('Read the weekly report of a site') and immediately enumerates the report's contents, so the agent knows exactly what it gets. It does not, however, differentiate itself from the close siblings weekly_site_report_history (past reports) or save_weekly_site_report (which presumably runs one) — the phrase 'Reading never runs the report' hints at the split but never names the alternative.

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?

The repeated 'Reading never runs the report' is a genuine usage signal — this is a pure read against an existing weekly artifact and will not trigger generation — which is exactly the confusion the sibling save_weekly_site_report creates. But the guidance is implicit: no explicit 'when to use this vs. weekly_site_report_history' or prerequisite statement (e.g. must the site be in a watch package, must a report already exist).

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