self_verify_candidates

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

Annotations declare readOnlyHint=false and idempotentHint=false, so the agent knows this tool can mutate state, but the description's word 'Export' suggests a pure read and never mentions that save_state=true writes a snapshot to issueops state. With no explanation of the write path or its side effects, the description adds nothing behavioral beyond the annotations and arguably works against them.

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?

A single front-loaded sentence with no wasted clauses; the verb and resource lead. It is dense with domain jargon ('curriculum', 'candidate') that the reader must already know, which slightly undercuts clarity.

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?

With no output schema, the description does useful work by naming the returned contents (open/satisfied IDs, next selected candidate). However, it leaves the non-read-only behavior undocumented and the term 'curriculum' undefined, so an agent still cannot fully predict the tool's effect.

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 both parameters are already documented in the input schema, including the default state key and the save_state meaning. The description adds no parameter-level meaning (e.g., what happens when state_key differs from an existing snapshot), so the baseline 3 applies.

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 has a specific verb ('Export') and a specific resource ('self-verification loop improvement candidate curriculum'), plus detail on what the payload contains (open/satisfied IDs, next selected candidate). It is clear what the tool produces, but it never distinguishes itself from close siblings like self_verify_history, self_verify_compare, or loop_status.

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?

There is no guidance on when to use this versus the other self_verify_* or loop_* tools, and no stated preconditions. The agent must infer the use case entirely from the name and the phrase 'candidate curriculum'.

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