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

The readOnlyHint=true annotation already declares that this is a safe read, so the description does not need to carry the safety profile. It does add value beyond the annotations by disclosing the location precondition (must be inside building type 35, Recruit Base) and the fact that refresh forces a re-fetch of the list. It says nothing about failure modes when outside the building, or about how the returned mission list is ordered or scoped, which limits it to a 3.

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?

Everything sits in one front-loaded sentence with the location parenthetical placed early so the agent can validate the precondition before acting. The clause chain of return contents is dense but scannable. Minor cost: the trailing 'refresh — ...' is glued on with a semicolon rather than given its own sentence, but nothing is wasted.

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 no-param read tool with no output schema, the description does the important work of enumerating what comes back (missions, departure time, prize, recruits, ammo tabs, draft notice), which is exactly what an agent needs in the absence of an output schema. What is missing is the linkage to the sibling tools that act on this state (sign_up, return), so the agent still has to guess how to proceed after reading.

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% for the single parameter, so the description has to compensate, and it does partially: 'refresh — заново запросить список' explains that the flag forces a fresh list fetch rather than a cached one. That is real meaning beyond the bare boolean type, but it does not say what the default behavior is or what changes in the response when refresh is set, leaving a notable gap for a 0%-coverage schema.

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 names the resource concretely (the military enlistment office) and enumerates exactly what the agent will get back: missions with departure time, prize and recruit squad, ammo tabs, and the draft notice in the backpack. It is not a bare restatement of the name 'game_military', but it never uses an explicit verb like 'returns/lists', and it does not distinguish itself from the siblings game_military_sign_up and game_military_return.

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?

Usage is implied rather than stated: the agent is told the office is inside building type 35 (Recruit Base), which is a real precondition for calling it, and the refresh parameter implies repeat/invalidation behavior. However, there is no explicit 'use this when...', no mention of when game_military_sign_up or game_military_return should be used instead, even though they are the obvious alternatives.

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