approvals_get_all_pending

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

With no annotations provided, the description carries the full behavioral disclosure burden. It correctly signals a read operation ('Returns') and adds the useful scoping trait that results are limited to what the calling user can action. It does not disclose return shape, grouping, ordering, or pagination behavior, but the zero-parameter surface keeps this a moderate rather than severe gap.

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 entire description is one front-loaded 18-word sentence: the verb and resource come first, the type enumeration is parenthetical, and the scope qualifier closes it. There is no filler, redundancy, or restatement of the tool name.

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 no-parameter, no-output-schema list tool, the description is largely complete: it states the resource, enumerates the covered request types, and scopes results to the caller's actionable items. The only omissions — result format and ordering — are minor for a list-all operation and partially inferable from the sibling getter names.

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 tool takes zero parameters and schema coverage is trivially 100%, so there is no parameter meaning for the description to add. Per the baseline rule for zero-parameter tools, a 4 is appropriate — the description's silence on parameters is correct and nothing is missing.

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 uses a specific verb and resource — 'Returns all pending approval requests' — and enumerates the three types (Instructions, Scheduled Instructions, Device Authorizations), which maps directly to the per-type sibling getters. The scope qualifier 'the calling user can action' adds further precision. An agent can distinguish this aggregate tool from approvals_get_pending_instructions, approvals_get_pending_scheduled_instructions, and approvals_get_pending_persistent_instructions without opening any schema.

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?

The phrase 'the calling user can action' implies the tool surfaces the caller's actionable approval queue, which gives reasonable context for when to call it. However, the description never explicitly states when to prefer this aggregate over the three type-specific sibling getters, nor does it name alternatives or exclusions. Usage guidance is implied rather than stated.

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