Veritula

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavioral detail beyond them: the reply ordering rules (criticisms first, pending first of all, then neutral comments) and the public/no-auth implication. No pagination or rate-limit detail is given, keeping it short of a 5.

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 verb+resource followed by return shape, with the sibling routing saved for the final clause. Dense but nearly every clause earns its place; the ordering enumeration packed into one sentence is slightly hard to parse.

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 one trivially documented parameter, the description carries the return-shape burden and does so well (title, description, idea tree, replies, ordering, brief vs full). It says nothing about size limits or truncation of the ideas tree, which is the remaining 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 coverage is 100% for the single id parameter, so the baseline is 3. The description goes further by giving the concrete address form veritula.com/discussions/<id> as an additional id source, which is real information the schema does not carry.

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 (gets a public discussion by id) and enumerates what comes back: title, description, ideas as a tree with their replies. It also distinguishes itself from get_idea by noting ideas are returned in brief.

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?

Tells the agent where the id comes from (search results or the discussion URL) and explicitly routes the agent: use get_idea when a full idea is needed rather than the brief form returned here. No alternative is left 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds context the annotations cannot: replies come back abbreviated and must be re-fetched individually, and it discloses the categories of reply (pending criticisms, addressed criticisms, neutral comments). No pagination or not-found behavior is mentioned, keeping it from a 5.

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 verb and resource are front-loaded, and the second half efficiently enumerates the return payload in one sentence. The mid-sentence sub-clause defining pending criticisms is dense but earns its place by explaining a domain-specific status. Slightly long, but no filler sentences.

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?

There is no output schema, so the description correctly carries the burden of describing the return shape: full Markdown text, the 'rationally adoptable' flag, what it replies to, and the three categorized reply groups. An agent can call it correctly, though error behavior for an invalid number 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?

With schema coverage at 100% for a single parameter, the baseline is 3, but the description meaningfully sharpens it by clarifying that the id is the site-visible number ('#123 on the site'), which disambiguates it from any internal identifier. That is a real addition over the schema's terse 'The idea's number'.

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 (gets) and resource (an idea, criticism or comment on Veritula) with the retrieval key (its number, #123 on the site). It also enumerates what is returned, making the purpose concrete. It does not, however, explicitly differentiate itself from the siblings get_discussion or search_ideas, 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?

Usage is only implied: the closing note 'Replies are given in brief; get them in full by their numbers' tells the agent to make follow-up calls with this same tool, which is a genuine usage hint. There is no explicit statement of when to prefer this over search_ideas or get_discussion, nor any exclusion, so it stays at the implied-usage 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?

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real behavior beyond that: relevance ordering, default listing when the query is empty, and that each result carries a 'rationally adoptable' verdict. It doesn't discuss pagination limits or result size, but the additions are substantive.

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 dense sentences with zero filler; core purpose and ranking lead, syntax rules follow, and the sibling cross-reference closes. Every sentence 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 exists, so the description carries the return-value burden and partially does so (results ranked, each marked adoptable). It omits the shape of a result (ids/titles) that the 'discussion' parameter depends on, keeping it short of fully complete.

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, but the description goes further by specifying query operator semantics (double quotes for exact phrases, leading minus for exclusions), which the terse schema description ('The words to search for') does 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?

Specific verb+resource ('Searches the ideas, criticisms and comments posted on Veritula') with the ranking behavior ('most relevant first') stated up front. It also differentiates itself from the sibling get_idea by saying get_idea returns an idea 'in full, with the criticisms and comments it got'.

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?

Explicitly states the no-query fallback ('Without a query, lists the newest ideas') and routes deep-dive readers to get_idea. It doesn't state when to prefer search over browsing a discussion, but the context for using it is clear.

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