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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description goes beyond by adding the required scope mcp:read and the conditional-null behavior of summary when army data is unavailable. It does not describe the failure mode when an id is missing or unauthorized, which is the main remaining behavioral gap.

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 dense sentences, front-loaded with the return contract and ending on the auth requirement. The middle sentence is a long enumeration of summary contents but every item is a field the caller will encounter, so it earns its length.

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 takes on the return contract: it names both top-level parts (summary, roster), the null condition, and cross-references save_roster for the shape of a roster rather than re-documenting it. A brief note on what happens for an unknown/inaccessible id is the only material omission.

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 0%, so the description must carry the parameter meaning, and it does: the single id identifies a roster owned by the caller and should come from list_my_rosters, which is exactly the provenance an agent needs. It adds no format or bounds detail beyond the schema's min/max length, but the provenance guidance is the non-obvious part.

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 concrete verb (returns) and resource (one roster), scoped to the signed-in player and keyed by an id drawn from list_my_rosters. An agent can immediately distinguish this from list_my_rosters (list vs. single) and save_roster (write).

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?

'by an id from list_my_rosters' names the sibling to call first and thereby establishes the lookup sequence, and 'owned by the signed-in player' rules out cross-user reads. It stops short of stating what happens when the id is unknown or not owned, or naming an explicit alternative for that case.

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