Kürsüde

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely useful non-annotated context: the tool does not call a model, so the agent itself must author the plan and teammate responses. This is exactly the kind of behavioral disclosure annotations cannot carry.

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 compact sentences with the purpose front-loaded, followed by the model-role caveat and the skip condition. No filler, though the opening 'kuralları döndürür' phrasing adds slight ambiguity.

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 an output schema present, return values need not be explained. The description covers what matters for invocation: what it produces, that the agent writes the plan, and the skip condition. Only the relationship to sibling briefings is unaddressed.

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 params (dil, rol, format, onerge, seviye) are fully documented in the schema. The description adds no parameter-specific detail beyond what the schema already provides, making the baseline 3 appropriate.

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 states a specific verb and resource (returns pre-match preparation rules) and characterizes the content (secret case plan per team, prep as the user's teammate), which distinguishes it from briefings like rakip_brifingi or poi_brifingi. It is slightly ambiguous about whether it returns rules or content, but the mechanism ('model çağırmaz; planı ve arkadaş cevaplarını sen yazarsın') clarifies.

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 an explicit when-not condition ('Kullanıcı hazırlanmak istemiyorsa atla') and an implicit when ('maç öncesi hazırlık'), but never names the sibling alternatives (rakip_brifingi, poi_brifingi) or the condition that would select one over another.

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 annotations already establish read-only, idempotent, non-destructive behavior, and the description adds important context: it does not call a model and only returns the criteria for the agent to perform the evaluation. It also summarizes the returned rubric contents, though it does not cover auth or rate-limit behavior.

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 compact and front-loads the main purpose before adding the important clarification that no model is called. The first sentence is dense but every clause contributes useful scope 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?

Given the output schema and annotations, the description provides everything needed: what the tool returns, that it is a read-only criteria lookup, and that the agent must perform the evaluation itself. No critical behavioral or usage detail appears 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 description coverage is 100%, so the parameters are already well documented in the schema. The description does not add meaning beyond the schema for dil, rol, format, or onerge, so the baseline score of 3 is appropriate.

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 states a specific verb and resource: it returns Kürsüde jury criteria and report format for the agent to use. It clearly separates this from briefing/list tools by focusing on evaluation criteria, though it does not explicitly name sibling tools.

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?

It gives a clear usage context: use this when the agent needs the jury rubric to evaluate the user's debate speech. It does not provide when-not-to-use conditions or named alternatives, so it stops short of the top score.

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 readOnly, idempotent, non-destructive and closed-world. The description adds value beyond that: the content boundary (Turkish vs English topic exclusion), filterability, and the reusable identifier format (e.g., o011) — non-obvious behavioral context an agent needs to chain tools.

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 tight sentences with the core purpose front-loaded and no filler. Density is high but every clause (content scope, filtering, id reuse) carries 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?

An output schema exists, so return-value explanation is unnecessary, yet the description still supplies the key chaining detail (id format usable in other tools). Combined with the content scope and filtering note, an agent has everything needed 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?

With schema description coverage at 100%, the schema already documents every parameter including enums, difficulty scale and the rastgele/adet trick. The description only echoes category and difficulty filtering, adding little beyond structured data, so 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?

The description names a specific verb and resource ('münazara önerge bankasını listeler') and scopes the content precisely (Turkish has 120 items, English excludes Türkiye gündemi). An agent can immediately tell this is a listing/search tool distinct from the sibling brifingi tools.

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?

It states that results are filterable by category and difficulty and notes the workflow ('Dönen kimlik diğer araçlarda kullanılabilir'), giving clear context for when this is the entry point. It stops short of explicitly naming when to use a sibling or any exclusions beyond the content note.

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 establish that this is read-only, idempotent, non-destructive, and closed-world. The description adds useful behavioral context beyond that: it does not call a model, the agent must write the POI or response itself, and reply speeches have no POI. That is meaningful added transparency, though it does not cover auth or rate-limit behavior.

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 purpose is front-loaded in the first sentence, followed by mode semantics, a critical behavioral note, and a constraint. Every sentence contributes useful information, with no filler.

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?

Given 8 parameters, 100% schema description coverage, annotations, and an output schema, the description provides the necessary operational context: what the tool returns, how the two yon modes behave, that the model is not called, and where POI is absent. Nothing essential for correct invocation 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 description coverage is 100%, so the schema already carries most parameter meaning. The description still adds nuance for yon by explaining the POI direction in context and notes the reply-speech exclusion. It does not add much for the other seven parameters, but the schema does that work.

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 first sentence states a specific verb and resource: it returns point-of-information (POI) rules. The two yon modes further clarify what the tool covers. It does not explicitly differentiate itself from siblings such as rakip_brifingi or hazirlik_brifingi, so it is clear but not fully sibling-aware.

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 explains the two usage modes for yon and adds an explicit exclusion: 'Cevap konuşmalarında POI yoktur' (there is no POI in reply speeches). It does not name alternative sibling tools or say when to choose this over them, so it is clear context but short of full alternative 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?

Annotations already declare readOnlyHint=true and idempotentHint=false, and the description usefully explains why non-idempotency matters: 0-2 openings are randomly assigned, so repeated calls may differ. It also discloses that no model is invoked (latency/cost relevant) and adds a disclosure constraint about not surfacing openings prematurely — meaningful behavior beyond the annotations.

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?

Front-loaded with what is returned, followed by the authoring instruction and the disclosure caveat; every clause carries information. The parenthetical enumerations ('rakip ya da kullanıcının takım arkadaşı', '(düşük seviyelerde)') make it dense but not wasteful.

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 9 parameters, an output schema, and full annotation coverage, the description supplies the behavioral essentials an agent needs: it returns a briefing rather than a speech, the agent writes the speech, and openings must stay hidden pre-jury. The required 'onerge' parameter's role is left entirely to the schema, which is acceptable.

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 baseline is 3; the description earns a bump by adding conditional behavior tied to parameters — random openings are assigned only 'düşük seviyelerde' (seviye), and the speaker becomes a teammate when kullanici_rolu is supplied. These are effects the schema enums alone do not convey.

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 uses a specific verb and resource ('Kürsüde brifingini döndürür') and scopes it to the AI speaker who is the opponent or the user's teammate, which implicitly separates it from a self-prep briefing. It never names the sibling tools (hazirlik_brifingi, poi_brifingi), so the agent must infer the boundary rather than being told it outright.

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?

It states clearly when this applies (opponent or teammate speech) and what to do with the result: 'Model çağırmaz; konuşmayı brifinge uyarak sen yaz' — the agent must author the speech itself rather than expecting generated text. It also gives an output-handling rule: don't reveal the assigned openings before jury evaluation. No explicit when-not/alternative tool is named.

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