kernel_models_pending_migrations

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

With no annotations supplied, the description carries the full burden and does well: it declares read-only behavior, discloses that the scan spans both global config and per-agent chains, and explains why the state matters (404/403 mid-run). It omits ordering, pagination, and whether the check hits live upstream or only cron-cached state, which keeps it below a 5.

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-loaded with the verb and resource, then the payoff and the pointer to the write path — every clause carries information. The single heavily nested sentence with a parenthetical and em-dash aside is dense enough to slow parsing, so not a 5.

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 correctly compensates by stating what each entry contains (a suggested successor) and what the list means. For a zero-parameter diagnostic list tool this is close to complete; only return-shape details such as entry fields beyond the successor are unstated.

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, so the baseline of 4 applies; there is no argument whose meaning the description needs to clarify. A mention of whether any implicit scoping (e.g., agent filter) applies could have pushed it higher, but nothing is required.

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 specific verb (list) and a precisely bounded resource: configured model references in global config plus per-agent model_chain whose upstream model the discovery cron flagged as 'gone'. The scope constraint ('these would 404/403 mid-run') makes it unmistakable against the sibling kernel_models_apply_migration.

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?

Explicitly frames the tool as the read-only inspection step and routes the mutating follow-up to kernel_models_apply_migration, which is exactly the decision an agent needs. It stops short of stating when the check is unnecessary (e.g., no agents configured, or after a migration was already applied), so not a full when/when-not treatment.

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