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

Annotations already declare readOnly=true, openWorld=true, destructive=false, so the safety profile is covered. The description adds genuine value with the return contract (useful text per source plus [sN] ids), but says nothing about how many results come back, latency/cost of a live web search, or whether sources are persisted for later deck_read_source calls.

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?

One compact sentence front-loads the action and folds the return shape into the same clause, with no filler. The [sN] notation is dense but purposeful.

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 two-parameter read tool with full schema coverage, the description covers the action and the output well enough to call it. It is incomplete about the document_id relationship and about result volume/persistence, which matter for an open-world search whose outputs feed later deck_read_source calls.

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 both parameters are documented and the description's silence on them is acceptable at baseline. It nevertheless leaves the non-obvious part unexplained: why a web search requires a document_id, i.e., that results are scoped to or stored on that deck; it also omits the 1–4 query cap already stated in the schema.

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 a concrete verb and resource ("searches the web") and goes further by stating what comes back — the useful text of each source tagged with an id [sN]. That id hint implicitly links to deck_read_source. It does not, however, distinguish this tool from near-identical siblings like ads_research, landing_research, or deck_search_project, so an agent must infer that this is the deck-scoped variant.

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 statement of when to use this versus deck_search_project (search within the project) or ads_research/landing_research (same capability for other document types), nor any prerequisite or exclusion. Usage is only vaguely implied by the tool's presence in the deck_* family.

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