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

Beyond the annotations (readOnly=false, openWorld=true, idempotent=false), the description adds genuinely new behavior: an API key is required, submissions are capped at one per address per reporter per 15 minutes, and evidence must exclude personal data. What it does not disclose is what a successful call returns (report ID, status) or whether moderation can reject the report.

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?

Five short sentences, front-loaded with purpose, then prerequisites (API key), then input pointers, then the rate limit, then the guardrail. Every sentence carries a distinct constraint and nothing is repeated from the schema verbatim.

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-param, schema-fully-documented, no-output-schema write tool, this covers prerequisites, input sourcing, and rate limits well. The only gap is post-call expectations — the agent cannot tell the caller whether a report ID comes back or what a duplicate submission error looks like.

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 meaning the schema lacks: categories must be codes drawn from list_categories with worked examples (ssh,brute-force), and the comment content rule ('log lines, never personal data') constrains input in a way the schema's 'ideally the relevant log lines' does not.

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 ('File an abuse report against an address') plus the actor/scope ('that attacked a system you run'), which cleanly separates it from check_ip, get_reports, and the other read-side siblings. An agent can tell instantly that this is the write path.

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 an explicit trigger (an address that attacked your system), an explicit exclusion ('Only report real, observed abuse'), and routes to the sibling that supplies valid inputs ('Use category codes from list_categories'). The rate-limit sentence further tells the agent what will happen on repeat calls.

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