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

Annotations only supply readOnlyHint=false, so the description carries nearly the full burden and does well: it states explicitly that this WRITES stored state, that it is not safe to repeat blindly, that there is no re-seal, and it details both refusal preconditions. Gaps remain around auth mechanics (how 'maintainer' is established) and the role of the secret parameter.

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?

Three tight sentences, front-loaded with audience and action, then preconditions, then the write warning. Each sentence delivers new information and none is padding.

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 state-mutating, non-idempotent, maintainer-gated tool with no output schema, the description covers refusal conditions and repeat-safety well. The unsupported secret parameter and the absence of any indication of what a successful seal returns leave a small residual gap.

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 33% with only post_id documented. The description adds meaning for post_id ('the public post that pre-published this digest') and loosely for log via 'one chain's prefix', but the secret parameter is left unexplained in both schema and description. Baseline 3 is appropriate given partial schema coverage.

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 (seal) applied to a specific resource (a legacy manifest row over one chain's prefix) and scopes it to maintainers. It is distinguishable from sibling tools like legacy_manifest, seal, and seals, though the phrase 'over one chain's prefix' is jargon-heavy and carries meaning only a domain-aware agent will parse.

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?

Gives concrete conditions for use: maintainer only, refused unless the named public post has carried the exact digest for the full pre-publication interval, and refused entirely if a manifest already exists. It does not name a sibling alternative (e.g., non-legacy seal), which keeps it short of a 5.

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