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

The description explicitly describes a write operation — 'written with the caller as its author and audit-logged,' creating an overlay and running the scheduler — while annotations declare readOnlyHint=true. This directly contradicts the annotation and is a serious inconsistency (Annotation Contradiction). Aside from that, the validation, error code, and default-disabled details would otherwise be useful.

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 'SUPERADMIN ONLY' and the verb, then compresses validation, persistence, default state, error routing, and return shape into a few dense sentences. Nearly every clause earns its place, though the run-on structure packs a lot into single sentences.

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 complex write tool it covers auth requirements, validation pipeline, default-disabled behavior, error code for the conflict case, and the return object. Nothing an agent needs to call it correctly is missing, despite the annotation mismatch.

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: `enable` gates whether the scheduler fetches on its ttl while the edge_feeds lane is on, and `spec` is identified as the object edge_feed_draft returned (the admin view shape). This goes beyond the schema's bare 'true = enabled on save'.

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 precise verb+resource ('Save a feed spec ... as an Edge feed overlay') and pins the exact create path (POST /api/admin/edge/feeds). It explicitly distinguishes itself from edge_feed_draft by naming the draft object as its input, and from the PATCH-edit path by naming overlay_exists, so an agent can separate it from siblings without opening schemas.

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 explicit when-to-use (after edge_feed_draft, edited or not), the exclusion/alternative (an id that already has an overlay returns overlay_exists, use PATCH /api/admin/edge/feeds/<id> to edit), and the precondition (superadmin JWT). Routing to the alternative path is stated outright.

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