read_topic

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

With no annotations, the description carries the full burden. It usefully discloses ordering (chronological), cross-app scope, and the pagination mechanism via next_offset in the response, but says nothing about permissions, result size, or behavior of the day filter.

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 sentence, front-loaded with purpose and scope, with the prerequisite and pagination note appended compactly. 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 4-parameter tool with no annotations, no output schema, and 0% schema description coverage, one sentence is thin. Purpose and pagination are covered, but the day parameter and any return-shape detail beyond next_offset are missing.

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 0%, so the description must compensate. It clarifies that key must be an exact value obtained from list_topics and implies pagination covers offset/limit, but leaves the day parameter entirely unexplained.

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?

States a specific verb and resource ('Read chronological evidence across apps') plus the narrow scope (an exact topic key), and ties the input source to the list_topics sibling. It is clear what the tool returns, though it does not contrast itself against other read tools like read_observation or read_app_day.

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?

'for an exact topic key returned by list_topics' gives a clear precondition and prerequisite step, telling the agent to call list_topics first. It stops short of stating when another sibling read tool would be preferred instead.

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