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

Annotations already cover read-only, idempotent, non-destructive, so the description correctly spends its words elsewhere: newest-first ordering, exactly which record types appear in the feed, and the permission scoping note ('Only what this app may read is in it'), which is genuinely useful context not in any structured field. It does not disclose the result cap or pagination behaviour visible only in the schema's limit description.

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?

Roughly three sentences, front-loaded with the ordering and contents, with no filler. The punctuation is a bit list-like but every clause carries information about what the feed contains.

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 correctly enumerates the payload's component record types so an agent knows what comes back. Remaining gaps are modest: no statement about result volume/pagination, and the internal mismatch between the schema's limit maximum (500) and its note that 'more is cut to 50' is 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 coverage is 100%, so all three parameters are already documented, including the day-level semantics ('on or after this day') and the truncation cap. The description's 'since is a day' restates the schema rather than adding format or interpretation beyond it, so baseline 3 applies.

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 specific verb+resource (return one merchant's activity timeline) and enumerates the record types included: calls with outcome and summary, notes, inbound texts/emails, outbound emails, tasks, deals. The 'one feed' framing implicitly differentiates it from the single-entity list_* siblings, though it never names an alternative 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?

It gives concrete usage contexts ('what happened since', 'catch up on a lead'), which is more than most tools offer. It stops short of stating when NOT to use it — e.g. pointing at search_calls, list_notes, or list_tasks when only one record type is wanted.

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