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

Annotations already cover read-only/idempotent/non-destructive, and the description adds substantial context beyond them: endpoint allowlist validation, POST/PUT/DELETE blocking, the static agent_directive routing block, the 40-field properties cap, and an explicit untrusted-content warning against executing ERP free text as instructions. This is unusually rich disclosure.

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?

Front-loads the 'LAST-RESORT' verdict, then usage rules, then args, then returns in clearly labeled sections; every sentence carries information. It is long, but the length is justified by the tool's open-ended generality, with only minor tightening possible.

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?

The Args and Returns sections cover endpoint shapes, param constraints, and the four response envelopes ('entity'+'id'+'result', 'result', 'count', 'results'), including null-stripping. Despite an output schema existing, nothing an agent needs to invoke or interpret this tool is 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 description coverage is 0%, so the description must carry the full burden and does: it documents endpoint syntax with four concrete examples, the count/singleton/sub-path special cases, the method restriction, and the full params key vocabulary including filter operator normalization (-gte/-lte to -ge/-le) and the 4096-char cap. Only correlation_id goes unmentioned.

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?

Names a specific verb+resource (generic GET over the weclapp API) and immediately frames its role as a last-resort escape hatch, which distinguishes it from every sibling. The scope, allowlist constraint, and supported endpoint shapes are all stated up front.

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?

Explicitly enumerates the preferred alternatives (search_entities, get_entity, find_reconciliation_candidates, verify_purchase_invoice, get_reference_data, tenant_health_check), declares misuse of them a 'tool-selection error', and gives the ONLY three legitimate use cases. It also states hard exclusions (no writes, no downloads) with the correct replacement tools.

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