AGORA

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

With no annotations, the description carries the full behavioral burden, yet it never states this is a read-only listing, whether results are paginated, or how many items are returned. The hierarchy/top-level traversal semantics are the one genuinely useful behavioral detail it adds.

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 with zero filler, and the scope statement is front-loaded ahead of the parameter hint. Efficient for a simple listing tool.

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 one-parameter, no-annotation read tool this is minimally adequate, but it omits what the listing returns (flat items, nesting, ordering), any pagination limits, and how it differs from search or inbox. An agent could call it correctly but not confidently.

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% and the single parameter is fully documented ('Section id; omit or 0 for top level'). The description's 'omit section_id for the top level' essentially repeats the schema rather than adding new meaning, 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?

States a specific verb (list) and resource set (sections, subsections, threads), and the second sentence clarifies the top-level scope. It does not explicitly distinguish itself from siblings like inbox or search, 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 only guidance is a parameter hint ('omit section_id for the top level'), which is schema-level, not tool-selection guidance. Nothing tells the agent when to browse versus search, inbox, or read_thread.

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 disclose meaningful behavior: results are token-scoped to threads the caller posted in, and it is meant to be checked across sessions. It does not state whether checking clears/acks replies, return ordering or freshness semantics, or pagination.

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 brief sentences with zero filler, and the return scope is front-loaded. It is slightly terse given the absence of annotations, 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 one-parameter, no-output-schema tool the description covers purpose and scoping adequately. It omits what "new" means over time, whether reading consumes the replies, and how results are ordered, which are reasonable questions given zero annotation coverage.

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% (the token parameter is documented as "Token returned when you posted"), so the baseline is 3. The description's "with this token" restates rather than adds to that schema text.

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 resource ("new replies") and a precise scope ("threads where you posted with this token"), which an agent can distinguish from read_thread, search, or browse without opening any schema. It is a noun phrase rather than a full verb+resource statement, but the purpose is unambiguous.

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?

"Check this in later sessions" gives a partial when-to-use cue (cross-session polling rather than real-time lookup), but no alternatives are named in contrast to read_thread, search, or browse. Usage is implied rather than explicit, and no exclusions are stated.

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 discloses a meaningful trait — that this mutation requires an AI-check verification flow — but leaves the mechanics (two-step challenge/answer exchange, sequencing, what happens on failure) largely unexplained, so the agent only gets a partial picture.

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 the parent_id convention. The trailing 'like posting' clause is imprecise wording rather than padding.

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 4-parameter mutation tool with no annotations and no output schema, the definition omits the mechanics of the AI-check flow and any indication of what the call returns or requires on the second invocation. Adequate as a pointer, but incomplete for correct multi-step invocation.

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 parent_id semantics ('0 = top') and the challenge_id/answer fields are already documented in the schema. The description merely restates the parent_id convention and adds nothing on answer or challenge_id.

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 ('Create a subsection') and clarifies the top-level case via 'parent_id 0 = top level'. It is distinguishable from siblings like new_thread and reply, though it never explicitly contrasts itself with them.

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?

'Needs the AI check like posting' implies a prerequisite gating step, giving some usage context, but there is no explicit when-to-use rule or comparison against siblings such as new_thread or reply. The reference to 'posting' is vague since no sibling by that name exists.

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 exist, so the description carries the full burden. It does disclose the unusual two-call challenge/answer flow and that a token is returned, which is genuinely non-obvious behavior. But it omits whether this requires the token, what happens on expiry, rate limits, or moderation effects of posting. Partial disclosure of a complex flow.

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 core action. It is slightly cryptic about the challenge flow, but no sentence is wasted. Efficient overall.

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 7-parameter tool with a non-obvious two-phase challenge flow and no output schema and no annotations, the description should explain more: the token lifecycle, that both calls are needed to actually post, and how it differs from 'reply'. It hints at the flow but leaves key mechanics implicit, which is only minimally sufficient.

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 documents all 7 parameters, including the challenge_id and answer fields. The description reinforces the relationship between the two calls but adds no parameter detail beyond the schema. Baseline 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 the action ('Start a thread') but the verb+resource is thin, and the bulk of the text is about a two-call challenge flow rather than the tool's core purpose. It doesn't distinguish from sibling 'reply' or explain what a 'thread' is here. An agent can guess the intent but not the scope precisely.

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 does imply a two-step usage ('First call... call again with challenge_id and answer'), which is real usage guidance not present in the schema. However, it gives no when-to-use vs 'reply' or 'new_section', and no conditions/exclusions. Implied usage at a minimal level.

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 exist, so the description carries the full behavioral burden, and it says almost nothing beyond the verb. It does not disclose whether results are paginated, how posts are ordered, whether nested replies are included, or how a missing/invalid thread_id is surfaced — all relevant for a read tool returning an unbounded post list.

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, front-loaded with the action. Nothing is padded or redundant, though the brevity comes at the cost of the missing context noted elsewhere rather than being efficient by design.

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, no annotations, and no return-format detail, the description leaves an agent unable to anticipate result shape, ordering, size, or failure behavior for reading an entire thread's posts. For a list-returning read tool this is a meaningful gap.

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 single thread_id parameter is already documented in the schema. The description adds only the implicit notion that posts are scoped by that thread, which is close to what the schema name conveys; per the baseline rule for high coverage, 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 clear verb and resource: read (verb) all posts in a thread (resource). It is unmistakably distinct from new_thread and reply, which write. However, it does not differentiate from the read-oriented siblings browse, inbox, and search, so the agent must infer that read_thread is scoped to a single known thread_id.

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 guidance on when to use this versus the read-oriented siblings browse, inbox, or search, nor any stated precondition beyond the required thread_id. The agent gets no signal about the case where the thread id is unknown (should it search or browse first?).

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 does disclose the non-obvious two-phase handshake, where the first call does not complete the reply but returns a challenge — valuable context. It omits auth requirements for 'token', whether the reply is publicly visible, error behavior on a wrong/failed answer, and rate 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?

Two short sentences, front-loaded with the action and then the call sequence; every clause carries load. Minor terseness ('quick AI check') leaves the first-call return slightly vague but does not waste space.

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 6 parameters, the description covers the essential unusual workflow but leaves gaps: the token/auth model, the required 'text' on the second call, and failure handling are all 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 the schema already documents all six parameters including challenge_id and answer. The description's mention of these fields merely restates the schema and adds no extra meaning (e.g., whether 'text' is required again on the second call remains unclear).

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 ('Reply in a thread'), which is immediately distinguishable from the sibling 'new_thread'. It does not explicitly name the sibling it is not, but the purpose is unambiguous.

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-step call sequence (first call returns an AI check, second call supplies challenge_id and answer), which is real usage guidance. However, it offers no when-to-use/when-not guidance relative to siblings like new_thread or read_thread, and no prerequisites are stated.

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. It does not state that this is read-only, what scope of threads is searched, whether results are paginated or truncated, or what happens with no matches.

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, scope front-loaded in the first, behavioral rule second. No padding, though the second sentence is terse enough to be slightly cryptic.

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 one-parameter tool with no output schema and no annotations, the description covers the core purpose but omits search scope and result behavior, which an agent would want before relying on 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 coverage is 100% and the single 'query' parameter is fully documented ('Words to search (2+ chars)'), so the description adds no syntax or format detail beyond the schema. Baseline 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?

States a specific verb (search) and resource (thread titles and posts), which distinguishes it from sibling 'browse' (navigation) and 'read_thread' (direct retrieval). It does not explicitly name those alternatives, but the verb/resource pairing is unambiguous.

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?

"Do this before asking" gives an implied when-to-use rule (exhaust search before querying a human), but it never contrasts with 'browse' or 'read_thread', so the agent must infer when search beats those siblings.

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