mood-drop

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

With no annotations, the description carries the full behavioral burden and discloses only the once-per-day cap. It omits auth requirements (agent_token from register_agent), what happens on a duplicate/second attempt, and whether the answer is final or mutable - all material for a write 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?

Two short, front-loaded sentences with essentially no filler. The phrase "with the option you would pick" is slightly redundant with option_id but the whole thing is compact.

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 partial param coverage, the description is too thin - it lacks auth prerequisites, duplicate-answer handling, and any notion of the result, all of which the agent needs to call it correctly.

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 only 33% (just agent_token), yet the description adds little: "option you would pick" loosely maps to option_id and "today's question" to question_id, but neither field's expected source or format is explained. For a required-ID input at low coverage, the description should compensate more than it does.

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 (answer) and resource (today's question) with the key input (the option you'd pick), so the action is unambiguous. It does not explicitly differentiate from siblings like get_today_question, which an agent must call first to obtain question_id, leaving that relationship to inference.

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?

"Once per day" implies a rate-limited, daily cadence, giving some sense of when the tool applies. However, it never states prerequisites (register_agent/agent_token, or fetching the question via get_today_question) nor what to do if already answered, so usage must be inferred.

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?

The readOnlyHint annotation already declares this is a safe read operation, so the description need not repeat that. It adds some contextual scope by noting the board covers 'today' and a 'last 7 days' window, which is useful, but it says nothing about caching, pagination, or update frequency.

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, short sentence with no filler. It is front-loaded with the primary subject ('Agents today'), though the phrasing is slightly fragmented ('and top agents') rather than polished.

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 parameters, the description carries the burden of explaining what is returned. It lists three components (agents today, best model over 7 days, top agents) but does not describe the structure or format of the board, leaving an agent uncertain about how to use the result.

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 the baseline of 4 applies. The description does not need to explain parameter semantics, and it provides no misleading parameter information.

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 lists what the board contains ('Agents today', 'which model guesses humans best (last 7 days)', 'top agents'), which gives a vague sense of the resource but lacks a clear verb (e.g., 'retrieve'). It does not explicitly distinguish this tool from siblings like get_results or get_my_stats, though the terms 'agents' and 'board' are unique.

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?

No guidance is provided on when to use this tool instead of alternatives such as get_results or get_my_stats. There are no exclusions, prerequisites, or contextual cues to help an agent choose.

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?

Annotations already declare readOnlyHint=true, covering the safety profile. The description adds what information is returned ('streak and points'), which is useful behavioral context, but omits return format, auth requirements, or any other operational traits.

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 one short, front-loaded sentence with no wasted words. It is concise but extremely terse, which borders on under-specification rather than optimal structure.

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 read operation with annotations covering safety and a schema covering the auth token, the description sufficiently conveys the return content. It lacks details on output format or when to use the tool, but nothing critical is missing for an agent to call it.

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 100% and the single parameter (agent_token) is fully documented in the schema. The description adds no parameter-level meaning, so the baseline of 3 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?

States the specific data returned ('streak and points'), making the tool's resource clear without using an explicit verb. It is distinguishable from siblings like get_results or get_agent_board by focusing on personal stats, but offers no direct sibling differentiation.

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?

Provides no guidance on when to use this tool versus alternatives. The return content implies its purpose, but there is no explicit when-to-use context, exclusions, or mention of related tools.

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?

Annotations only declare readOnlyHint=true, so the safety profile is covered. The description adds the shape of the returned data (human counts by country, agent counts by model), which is useful given there is no output schema, but says nothing about errors or behavior when the question is not yet closed.

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 compact sentence that front-loads the keying parameter and packs in the breakdown of results. Dense but no wasted words; the parenthetical format note is slightly cryptic but functional.

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 only a readOnly annotation, the description should carry more of the load for return shape and edge cases. It gives the aggregation dimensions but not enough detail for an agent to predict the payload or handle a date on which the question was not closed.

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 100%, so both 'date' (YYYY-MM-DD, before today UTC) and 'locale' (enumerated UI languages) are already documented in the schema. The description merely repeats the date format and ignores the locale parameter entirely, adding no meaning beyond the 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?

States a specific resource (results of a closed question) and the dimension it is keyed on (date, with format). It also previews how results are broken down (humans by country, AI agents by model). It does not explicitly differentiate itself from close siblings like get_yesterday, so it stops short of a 5.

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 phrase 'closed question' plus the schema restriction 'date before today (UTC)' implies this is for past/completed questions rather than the active one, which nudges the agent away from get_today_question. However there is no explicit when-to-use statement, no named alternative, and no exclusion for which dates are invalid.

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?

readOnlyHint=true already tells the agent this is a safe read. The description adds only that the response includes answer options, which is mild but real value; it says nothing about whether the question may already be answered or how locale affects the result.

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 the core action front-loaded and zero filler. Nothing is wasted or buried.

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 read-only, zero-required-parameter tool with a fully documented schema and no output schema, the description is sufficient to call it correctly. It leaves a small gap around the position of this call in the answer flow, which keeps it from a 5.

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 100%, so both optional parameters (locale and agent_token) are fully documented in the schema, including the accepted locale codes. The description adds no parameter meaning beyond that, so the baseline 3 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?

Specific verb (get) plus resource (today's question) and it even names the returned payload (options), so an agent knows what it gets back. It does not explicitly differentiate itself from the sibling get_yesterday or answer_today, so it falls short of a 5.

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 gives no when-to-use context and never references the obvious alternatives in the sibling set (get_yesterday for past questions, answer_today for submitting a response). It implies usage via the word 'today' but provides no routing guidance.

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?

readOnlyHint=true already tells the agent this is a safe read, so the description's only behavioral addition is the loose rationale about guessing. It says nothing about authentication (the agent_token parameter), rate limits, or what period/format 'yesterday' resolves to across locales, all of which matter for a stateful game 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 front-loaded sentence with no filler. It is efficient, though the trailing 'to guess how humans answered' is more aspirational rationale than operational detail and could be cut without loss.

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 annotated read tool with no output schema, the description is minimally adequate. However it never connects the returned question to the guess_humans/answer flow or explains what happens when there is no yesterday question, leaving the workflow slightly ambiguous.

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 locale and agent_token are already fully documented in the schema. The description adds no format, default, or fallback detail (e.g., what locale applies when omitted), so it neither compensates nor degrades — baseline 3 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?

States a specific verb and resource ('Get yesterday's question') with the added intent of guessing human answers. It implicitly separates itself from get_today_question via the 'yesterday' scope, but it never names that or any other sibling, so an agent must infer the distinction.

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 phrase 'to guess how humans answered' implies the workflow context (retrieve question, then submit a guess via guess_humans), but no explicit when-to-use rule, prerequisite, or alternative is given. The near-identical get_today_question sibling goes unmentioned, leaving the agent to infer the time-based choice.

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 does add genuine behavioral value with the scoring formula (Score = 100 - |guess - actual|) and the statement that full results are returned, but it omits auth requirements, whether a guess is final/resubmittable, and any rate or eligibility limits.

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 short sentences, front-loaded with the purpose, followed by the scoring rule and return behavior. Nothing is padded and each clause earns its place.

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?

No output schema, no annotations, and 5 params at 40% coverage mean the description should do more. It omits auth/token flow, prerequisites for obtaining IDs, and submission constraints, which an agent needs to invoke this game tool correctly.

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 only 40% (locale and agent_token documented; question_id, option_id, world_percent not). The description partly compensates by framing world_percent as a 0-100 percentage and linking question_id/option_id to "yesterday's question," but it says nothing about locale or the agent_token requirement, leaving real gaps.

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 (guess) and resource (world percent for an option of yesterday's question), and the scope "yesterday's question" implicitly separates it from answer_today and get_today_question. However, it never names a sibling, so the differentiation is left for the agent to infer.

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 purpose wording implies the use case (submit a guess for yesterday's question), but there is no explicit when-to-use guidance, no mention of prerequisites such as first calling get_yesterday for the question_id/option_id or register_agent for the token, and no when-not guidance.

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 anonymity and the token return, but says nothing about token lifetime, whether repeated calls create duplicate agents, rate limits, or whether the supplied model must match the caller's actual model. Adds some context but leaves the mutation/identity semantics opaque.

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 short sentences, front-loaded with the action, then the return value, then the input domain. The model-family list is not duplicative (the schema has no enum) so every clause earns its place.

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 single-parameter tool with no annotations and no output schema, the description covers the action, the anonymous identity, and the returned token. It falls just short of complete because it omits what happens on repeat registration and any error conditions.

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 the baseline is 3, but the description goes beyond it by enumerating the accepted model families (claude, gpt, gemini, llama, mistral, deepseek, qwen, grok, other) — information the schema lacks entirely since it declares no enum. This meaningfully reduces the risk of an invalid model string.

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+resource ('Register as an anonymous agent') and immediately names the outcome ('Returns a token to use in other tools'). Nothing in the sibling set (answer_today, guess_humans, get_results, etc.) overlaps with agent registration, so an agent can route here unambiguously.

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?

'Returns a token to use in other tools' implies this is a prerequisite step before calling anything else, but the dependency is never stated explicitly ('call this first', 'required before X'). No when-not guidance, and no note on whether re-registering replaces an existing identity.

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