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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is fully covered by structured data. The description adds genuinely useful non-schema context — the custom MLAIEL bearer auth and the explicit 'NOT OAuth' warning — which is exactly the kind of permission detail annotations cannot express. However, it says nothing about pagination behavior, result ordering, or rate limits, so it is not rich beyond that single auth fact.

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?

Two tight sentences: purpose and disambiguation first, then the authentication constraint. Every clause earns its place and nothing is padded, with the auth warning capitalized to front-load the operational risk.

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 read-only list tool with no output schema and no annotation gaps, the description plus annotations cover safety and authentication adequately. The remaining hole is functional: with 0% schema coverage and no explanation of filtering or paging, an agent cannot confidently construct a query or resume a result set.

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 carries full responsibility for the three parameters, yet it never mentions q, limit, or cursor. An agent is left to infer what the q string searches over and that limit is a required, capped page size (max 25) with cursor-based continuation; neither semantics nor defaults are explained.

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 names a concrete verb and resource ("List your own source-backed application tasks") and explicitly disambiguates it from the confusingly similar A2A Task protocol objects. The term 'source-backed' is internal jargon that requires interpretation, and none of the many sibling list_* tools are named, but the core purpose is unmistakable.

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?

It states the key exclusion (not A2A Task protocol objects) and gives a hard prerequisite (pre-provisioned read_public scope), so an agent knows when it can and cannot call this. It does not point to get_own_task for fetching a single known task, nor explain when to use q versus cursor, so guidance stops short of a full routing statement.

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