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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds two genuinely useful traits beyond that: a cursor-based pagination contract ('next' echoed back as 'before') and a degraded unauthenticated response shape ('signed_in:false'). The phrasing is terse and the auth condition ('a key') is never defined.

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?

Two short sentences, front-loaded with what the tool returns and followed by the paging mechanic. It is appropriately sized, though the trailing 'Without a key: signed_in:false' reads as a fragment that is hard to parse without surrounding context.

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?

There is no output schema, so the description carries the burden of describing returns; it references a 'next' field and a 'signed_in' flag that exist nowhere else in the structured data. For a simple annotated read tool this is borderline adequate, but it leaves the response shape and what counts as 'a key' unexplained.

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% and neither parameter is described in the schema, so the description must carry the load. It successfully explains 'before' as the cursor from a prior response's 'next', but 'limit' (1-50) is never addressed, leaving half the parameters undocumented anywhere.

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 resource and content: 'The account's recent calls and outcomes', which tells an agent this is an activity/history read rather than a config or search tool. It does not, however, differentiate itself from siblings such as 'profile', 'savings', or 'search', leaving overlap ambiguous.

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 an actionable rule for paging ('pass next as before for older ones') and implies an unauthenticated path ('Without a key: signed_in:false'), but never states when to prefer this tool over 'profile', 'savings', or 'search'. Usage is implied rather than contrasted with alternatives.

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