activity_log

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

With no annotations, the description carries the full burden and mostly delivers: it discloses the ordering, the returned fields (when, agent, tool, summary, undoable, undone), and that app-side edits are invisible to the log. It does not address pagination/limit behavior or any permission or retention constraints, which are the remaining behavioral gaps for a mutation-adjacent log.

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 description is dense but front-loaded: purpose and return shape first, then the undo handoff, then filter semantics, then the scope caveat. Every clause carries information, though the semi-colon-chained filtering sentence is slightly compacted and could be split for faster scanning.

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 read-only, four-optional-parameter query tool with an output schema and no annotations, the description covers purpose, ordering, fields, filters, the undo linkage, and the scope limit. Return-format detail is excused by the presence of an output schema; the only real omission is limit/pagination semantics.

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 0%, so the description must compensate and largely does: 'Filter by agent name or tool' explains the agent and tool params, and 'only_undoable hides the rest' explains only_undoable. Only 'limit' goes unexplained (its default of 20 and interaction with the 'newest first' ordering are left implicit).

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 states a specific resource (an audit log of changes made through this server) with its ordering (newest first) and explicit scope exclusion (changes made directly in the Calendar/Reminders apps are not recorded). It also names the sibling it pairs with ('Use the id with the undo tool'), so an agent can distinguish it from the mutate-family tools at a glance.

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 routing guidance ('Use the id with the undo tool') and a clear exclusion ('Changes made directly in the Calendar/Reminders apps are not recorded here'), plus how filters behave. It stops short of stating when to consult the log at all (e.g. before or after a mutation), so it is strong rather than complete.

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