sassy_update_apply

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

Annotations declare readOnlyHint=false and destructiveHint=false, but the description adds critical behavioral detail beyond that: it clarifies that it does NOT execute anything, describes the SHA-256 verification process (deleting file on mismatch and erroring, or warning and proceeding without a sidecar), and notes platform-specific behaviors like refusing .msi on POSIX. It also mentions the disabled condition for packaged builds. This is rich, non-contradictory transparency.

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?

Although the description is long, every sentence carries essential information and is logically ordered: starting with the core mutation/execution distinction, then requirements, then verification, then platform specifics, then disabled/build conditions and network requirement. There is no filler or redundancy; the structure front-loads the most critical safety information.

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 tool with no output schema and 0% parameter coverage, the description delivers everything an agent needs: the return value (local path plus run command), the required input and its source, optional parameters with defaults, verification behavior, platform-specific command generation, and operational constraints (network, disabled in frozen builds). No critical information is missing for correct invocation.

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 input schema only provides types and defaults, with zero description coverage. The description goes far beyond that: it explains that asset_name is required and must be an exact filename (and how to obtain valid names), that tag defaults to 'latest', and that dest_dir has OS-specific defaults (LOCALAPPDATA on Windows, ~/SassyMCP/updates otherwise). It also clarifies the meaning of optional parameters in practice. This fully compensates for the schema's lack of explanation.

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 opens with a precise statement of what the tool does and what it does NOT do: 'Mutating (writes a downloaded file to disk; does NOT execute anything)'. It clearly specifies the resource (release asset) and the action (download, write to disk, return path and command). This distinguishes it from sibling tools like sassy_update_list (which lists assets) and sassy_update_check (which checks for updates). The purpose is unambiguous.

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 explicitly tells the agent to get valid asset_name values from the sibling tool sassy_update_list, and clearly explains the optional parameters (tag, dest_dir) with their defaults and OS-specific behavior. It also states that it is disabled in packaged/frozen builds and requires network access. This fully orients the agent on when and how to use the tool versus alternatives.

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