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

Annotations declare readOnlyHint=false and idempotentHint=false but explain none of the why; the description fills that in well — calls mutate state by marking findings seen, the first call on a new connection returns every open finding, deduplication is once-per-open-finding across scans, and resolved status appears only if fixed by the next scan. This is exactly the stateful semantics an agent cannot get from the schema.

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 scoping and mutation behavior is front-loaded in the first sentence and the return-item shape follows logically. The peek/since semantics are stated twice — once mid-paragraph and again in the closing sentence — which is a small redundancy in an otherwise dense, efficient definition.

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, but the description compensates by describing the item fields (issue_id, status, evidence with secrets masked) and the newest-last ordering. Combined with annotations and full schema coverage, an agent has everything needed to invoke and interpret results correctly.

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 the baseline is 3, but the description adds real meaning: mark_seen=false is framed as a 'peek', site and since are both declared to not move the last-seen marker, and the limit behavior is framed as 'call again if more are waiting'. Minor overlap with schema text keeps it from a 5.

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 — 'Get the findings Wardzo detected on your monitored sites since this connection last checked' — with explicit scoping (background re-scans, re-checks, new sites, newest last). It is clearly distinguishable from list_issues (all findings) and get_report (aggregate), and even names explain_issue as the follow-up consumer of issue_id.

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?

Gives concrete when-to-use guidance: 'Use mark_seen=false to peek without marking' and 'since ... to list findings first seen after a time', plus the note that site filtering is also a peek. The gap is that it never contrasts this tool with siblings like list_issues or get_report, so the agent must still infer when the incremental view is the right one.

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