bunny_manage_edge_rules

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

Annotations already carry the mutation profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), so the bar is lower. The description adds the specific mutation semantics — 'delete' removes a rule, 'enable'/'disable' toggles it — which clarifies what gets destroyed. But it says nothing about authentication needs, live-traffic side effects, conflict behavior, or what happens on repeated calls, so it meets the baseline without going further.

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 opening sentences are well-structured and front-loaded, but the ActionType enumeration balloons to well over 200 entries, dominated by UnitTestValidate noise, and then degenerates into corrupted tokens ('253=UnitTestValidate…', 'and more', 'etc...'). The tail bloads the definition to thousands of tokens and degrades trust; the whole definition is not appropriately sized despite its strong lead.

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 four-action tool with a nested open object and no output schema, the description covers action selection and the main upsert payload fields well. It omits the Triggers item shape (array of what — TriggerType/Pattern fields), any result or confirmation format, and error semantics, which an agent will need on the first real upsert. This is adequate but has clear, nameable gaps.

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?

The schema describes edge_rule only as an open bag (additionalProperties: {}), so without the description an agent would have zero structure for the tool's most complex parameter. The description supplies the full field contract — ActionType, TriggerMatchingType (0=MatchAny, 1=MatchAll), Triggers, ActionParameter1/2, Description, Enabled — plus a numbered ActionType catalog (0 and up). This is precisely the semantics the schema fails to provide.

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 opens with a specific verb-resource pairing — 'Manage edge rules on a CDN pull zone' — and grounds it by explaining what edge rules control (redirects, headers, caching, origin routing). It enumerates all four operation modes (upsert, delete, enable/disable), making the scope concrete and clearly distinct from nearby siblings like bunny_manage_edge_script, bunny_manage_waf_custom_rule, and bunny_manage_rate_limit_rule. The corrupt tail of the ActionTypes list does not affect the core purpose statement.

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?

Operational usage guidance is explicit: it maps the upsert action to its parameter contract ('For upsert, provide edge_rule with…') and names what the other three actions do, with edge_rule_id required for them in the schema. However, no alternatives or when-not conditions are stated — the tool relies on its 'edge rules' subject to self-select against the 50+ siblings rather than exclusions or alternative routing.

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