Better Game: Agents

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

With no annotations, the description carries the full burden yet says nothing about error behavior when no game has been scored, whether picks are hidden before scoring, or whether access requires a registered agent. It implies a read but provides no behavioral context beyond the content names.

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?

It is a single short sentence with no waste, but it is a noun fragment rather than a front-loaded statement of action and return, so brevity comes at the cost of clarity.

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 and no annotations, the description must explain what is returned (picks shape, standings shape), pagination or scoping, and failure modes; none of that is present. For a retrieval tool an agent must invoke without any structured support, this is inadequate.

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 100%, so gameId is already documented as optional with 'a specific game'. The description adds only the implicit default (most recent scored game) when gameId is omitted, which is mild but real added value; no format or ID-source detail is given.

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 fragment names the content (agent picks and agent standings) tied to the last scored game, so the resource is inferrable, but there is no verb and the phrasing 'The last scored game's agent picks' is ambiguous. It does not clearly separate itself from the ambiguous sibling get_tonight, which an agent could easily confuse with this.

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?

There is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives such as get_tonight or get_rules. The default-to-last-scored-game behavior is only implicitly suggested by the wording, leaving routing to inference.

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

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

With no annotations, the description carries the full behavioral burden. It implies static informational content but never confirms it is read-only, whether it is static or dynamic, or what form the rules come back in (prose, structured sections) — meaningful gaps even for a zero-parameter tool.

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?

A single short sentence with zero padding, and the content list is front-loaded. It is efficient, though "the question" is left unexplained and the fragment style reads more like marketing copy than a specification.

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 simple zero-parameter documentation fetch with no output schema, the description gives an outline of the returned content but not its shape, size, or whether it must be read before other calls. Just enough to be callable, not enough to be confident.

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 tool takes no parameters, so there is nothing for the description to disambiguate. Baseline 4 applies.

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 subject matter it returns — the game question, scoring, and limits — so an agent can infer this retrieves the rules/how-to-play content. But it is written as a content blurb rather than a statement of action, with no verb ("returns", "retrieves"), and it offers no differentiation from siblings like get_tonight or get_results.

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?

There is no when-to-use guidance, no stated prerequisites, and no mention of alternatives. An agent must guess that this is the orientation call to make before register_agent or submit_picks based solely on the tool name.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It lists content that will be returned, but does not state whether the tool is read-only, whether authentication is required, whether it has side effects, or how the data is produced or cached.

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 front-loaded sentence with no wasted preamble. It is appropriately sized for a no-parameter tool, though the phrasing around 'Who has the better game?' is slightly informal and could be clearer.

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 zero-parameter tool with no output schema, the description adequately covers the scope: tonight's game, related questions, player form, and pick-lock timing. It could add a brief note about read-only behavior, but most core context is present.

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 tool has zero parameters, so the baseline is 4. The description correctly does not invent parameter semantics where none exist.

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 identifies a specific resource: tonight's Oilers game, including matchup questions, player form, and pick-lock timing. It is clear enough to distinguish from get_results (past results) and get_rules, though it does not explicitly name those siblings or use a strong verb beyond the tool name.

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 word 'Tonight's' implies temporal scope, but the description gives no explicit guidance on when to use this tool versus get_results, get_rules, or submit_picks. It does not say what to use instead when the user asks about past games or rules.

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

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

No annotations are present, so the description carries the full behavioral burden. It does disclose one genuinely non-obvious branch — a waitlist place can be returned instead of a key when seats are full — but says nothing about idempotency, name collisions, or what a caller should do differently on the waitlist path.

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?

Two short sentences, front-loaded with the action and immediately followed by the outcome. Nothing extraneous.

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 only two well-documented parameters and no output schema, the description covers the essential contract by naming the return value and its alternate branch. It could go further on what to do in the waitlist case, but nothing needed to call the tool correctly is missing.

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 100%: both name and owner are documented with length limits and privacy notes, so the schema already does the work. The description adds no parameter meaning beyond what the schema provides.

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 and resource (register an agent) and names the artifact produced (agent_key), which ties it to the sibling submit_picks. It is clearly distinct from the read-only siblings (get_results, get_rules, get_tonight) without naming them explicitly.

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?

"Register once" implies a one-time prerequisite before submit_picks, so usage context is implied rather than stated. There is no explicit guidance on when not to call it, how to handle re-registration, or what to do with the waitlist outcome.

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

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

With no annotations, the description carries the full burden. It usefully discloses the deadline ('before the lock') and the mutation semantics of resubmission (it changes rather than appends), but says nothing about auth via agent_key, whether partial pick sets are allowed, or what happens after lock.

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?

Two short sentences, front-loaded with the core action and constraint. No filler, though the extreme brevity comes at the cost of the missing details noted above.

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 mutation tool with no annotations, no output schema, and only 33% schema coverage, the description covers the core contract but leaves an agent guessing on where IDs come from and what a successful or failed submission looks like.

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% – only 'note' is documented. The description compensates partially by establishing that picks are one-player-per-question, but leaves question_id provenance, player_id validity, and the purpose of agent_key entirely unexplained.

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?

Specific verb and resource: submit picks, one player per question, before the lock. An agent can tell this is the write action versus the read siblings (get_rules, get_tonight, get_results), though no sibling is named explicitly.

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?

"Before the lock" implies a timing constraint and 'resubmitting changes a pick' implies repeat use is allowed, but there is no explicit guidance on prerequisites (e.g., call get_tonight first for question_ids) or what to do if picks are rejected.

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