Write Hermes deploy repair proposal

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds the valuable constraint 'performs no git, service, or config mutation' which clarifies the non-destructive nature beyond the annotations. However, it doesn't describe what the proposal artifact looks like, whether it requires authentication, or what happens to existing proposals (overwrite vs append). With annotations already clarifying the safety profile, the description adds marginal but useful context.

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 description is a single, efficient sentence that conveys purpose and safety characteristics without waste. It's front-loaded with the core purpose ('Write a proposal-only deploy repair artifact') and appends the crucial constraint. No filler or redundancy.

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 9 parameters, 0% schema coverage, no enums, and an output schema present (which the description need not explain), the tool is moderately complex. The description captures the core intent and safety posture but omits guidance on how deploy guard evidence is provided, which system/context this operates in, or what the produced proposal contains. For a proposal-generation tool paired with a separate apply tool, some handoff context would strengthen completeness.

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%, and the description mentions zero parameters. All 9 parameters (live_checkout, home, profile, toolkit_root, expected_branch, expected_commit, source_checkout, require_clean_live, compare_source_head) are documented only in the input schema. With 0% coverage, the description should compensate by explaining key parameters, but it offers no parameter guidance at all. Baseline 3 is slightly generous given zero compensating text.

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 clearly states 'Write a proposal-only deploy repair artifact based on deploy guard evidence' with a specific verb (write), resource (deploy repair artifact), and scope (proposal-only, based on deploy guard evidence). It distinguishes itself from the sibling 'hermes_deploy_repair_apply' which handles actual application. Does not explicitly name the applying sibling, but the proposal-only contrast is clear.

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 description states this tool performs 'no git, service, or config mutation', which effectively differentiates it from hermes_deploy_repair_apply and other mutation tools. It's based on 'deploy guard evidence', clarifying that it should be used after deploy guard check output. However, it doesn't explicitly name the alternative (hermes_deploy_repair_apply) or state when NOT to use it, and doesn't describe prerequisites like running deploy_guard_check first.

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