Victano: EU tenders and grant calls

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

With no annotations provided, the description fully discloses important behaviors: it sends an email, generates a six-digit code valid for 15 minutes, returns a request_id, and does not charge or require a card. This is substantial behavioral context beyond what structured fields provide.

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 concise sentences with no wasted words. The action is front-loaded, the flow is clear, and every sentence contributes essential procedural or safety 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?

For a simple one-parameter tool with no output schema and no annotations, the description covers the input, the outcome, the timeout, the returned request_id, and the next step. An agent has enough information to invoke it correctly without further clarification.

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 schema only lists 'email' with no description, while the tool description adds that it should be the user's work email. This provides meaningful semantic guidance for the single parameter, partially compensating for the 0% schema coverage.

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 clearly states it begins authentication by sending the user's work email, which is a specific verb and resource. It also differentiates itself from its sibling connect_verify by naming it explicitly and describing the flow.

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 explains when to use this tool: to start authentication. It also explicitly instructs the agent to call connect_verify with both the code and request_id afterward, providing clear sequential guidance and distinguishing from the alternative.

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 fully carries the behavioral burden: it discloses immediate session authentication, no reconnect, full toolset availability, one-time key display, and the need to persist the key. This is rich, useful transparency beyond what the schema could convey.

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 concise and front-loaded with the core action. Each subsequent sentence adds necessary operational detail — success behavior, persistence requirement, and one-time key warning — without any 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?

For a verification tool with no annotations and no output schema, the description covers the essential call context, success semantics, and what to do with the returned api_key. Nothing important is missing for an agent to invoke 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?

The schema provides only parameter titles, but the description supplies the meaning and format: request_id comes from connect_start and code is a six-digit value the user received. It also references the returned api_key, fully compensating for 0% schema description coverage.

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 action — 'Complete authentication' — with the two required inputs and explicitly references the predecessor connect_start. This clearly distinguishes the tool from the read/workflow siblings and from connect_start, which starts rather than verifies the connection.

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 names connect_start as the source of request_id and specifies the six-digit user-received code, establishing exactly when this tool is used in the connection flow. It doesn't spell out explicit exclusions such as 'do not call before connect_start', but the context is clear.

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?

There are no annotations, so the description carries the full behavioral burden. It does disclose the return scope (normalized record plus document inventory) and implies that eligibility text is NOT included by pointing to read_document. However, it does not mention side effects, authorization requirements, or what happens when both parameters are supplied.

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-loaded: the core return value appears first, followed by actionable usage guidance. Every sentence earns its place, including the domain-specific Lithuanian vocabulary note, which adds contextual value without bloating the text.

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 low-complexity tool with no output schema and no annotations, the description gives a useful overview and workflow, but it lacks parameter disambiguation. The return value is only loosely described as 'full normalized record plus document inventory', which may not be sufficient for an agent to interpret the response 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 0%, and the description adds no parameter information at all. It never explains the difference between 'id' and 'opportunity_id', whether they are aliases, or which one should be supplied. The parameter names are mildly self-descriptive but insufficient to reliably guide a correct call.

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 resource ('one opportunity') and clearly distinguishes the full record from a 'search card', which maps to the sibling search_opportunities tool. The title and first sentence together establish exactly what the tool retrieves: a full normalized record plus the document inventory.

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 explicit when-to-use guidance ('Use before advising on a bid'), an explicit exclusion ('a search card is not enough'), and a follow-up step ('Follow with read_document for eligibility text'). This provides clear operational context without needing to infer anything.

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 burden, and it does add meaningful behavioral context: the output is a full procedural playbook, not a summary, and the agent should follow it. However, it does not disclose behavior around ambiguous optional identifiers, what happens when no identifier is provided, error cases, or whether this is a pure read operation beyond what the name implies.

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-loaded with the core purpose. The final instruction to follow rather than summarize earns its place by shaping agent behavior, and there is no redundant or filler language.

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?

The tool has three optional params, no output schema, and no annotations, so the description must cover both selection semantics and expected results. It ably describes the nature of the returned playbook but omits how to identify the workflow correctly, leaving a meaningful gap for correct 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 description coverage is 0%, so the description needed to compensate, but it only mentions 'one workflow id' without explaining the relationship among the three parameters: id, name, and workflow_id. It does not say which parameter to prefer, how they interact, or what happens when multiple or none are supplied, leaving genuine ambiguity.

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: it returns "the complete step-by-step playbook for one workflow id" and details what it contains (decision gates, EU procurement specifics, pitfalls). This clearly separates it from sibling list_workflows, which would provide an overview rather than the full playbook.

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 useful instruction on how to treat the result ('Follow it rather than summarising it'), and the 'one workflow id' phrasing implies a single-workflow lookup. However, it does not explicitly state when to choose this over siblings like list_workflows or search_opportunities, nor does it describe any exclusions or prerequisites.

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 must carry behavioral disclosure. It adds useful behavior (persona affects which workflows appear) and a procedural warning, but it does not state whether the operation is read-only, what the return value looks like, or any error/edge-case 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?

Three short sentences: the first explains what the library contains, the second gives a high-priority instruction, and the third covers filtering and the follow-up call. 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?

For a one-parameter listing tool, the description covers scope, filtering, and next-step routing. The only notable gap is the absence of explicit return-format or output details, which would help an agent consume the results; with no output schema, that burden falls on the description.

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 0%, but the description compensates by explaining the persona parameter's effect with a concrete example ('Pass persona='consultant' to see the multi-client ones'). It doesn't enumerate all valid persona values, but for a single optional parameter this is meaningful guidance.

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 title and description clearly identify this as a listing tool for available playbooks/workflows, and the description enumerates the workflow stages it covers. It also distinguishes itself from get_workflow by directing the agent to follow up with that tool.

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 explicit timing guidance ('READ A WORKFLOW BEFORE IMPROVISING A PROCESS') and tells the agent to chain it with get_workflow. It doesn't explicitly state when not to use it versus other sibling tools, but the intended call sequence is clear.

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 and does so exceptionally well. It discloses non-obvious behavior: multi-lot collapse, no English translation of notice titles, measured recall differences by language, exclusion of notices without NUTS codes, value-filter exclusion rather than guessed pricing, coverage-block semantics, and strict-flag 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 an unbroken, very long paragraph with no bullets, headings, or parameter-grouped structure. It starts with a large language-phrase list before core usage rules, making it hard to scan. Nearly every sentence carries information, but the delivery is far from concise or well-structured.

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 26 parameters, no annotations, and no output schema, the description is unusually complete: it covers filter semantics, defaults, response card shape, coverage reporting, multi-lot behavior, and downstream tools. It still leaves some gaps around limit/pagination behavior and a few niche parameters, so it is not 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 description coverage is 0%, so the description is the only parameter documentation. It explains most key parameters well: cpv prefixes, status values, ISO dates, EUR value conversion, criteria_stated, no_guarantee, strict flags, source, type, contract_nature, queries vs query, fields, and exclude_results. A few parameters such as kind, value_band, cpv_divisions, lang, and limit remain 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?

Title and opening 'Hybrid search' make the subject immediately clear: it searches tenders and grant calls. The description also positions it as a recall-oriented search tool and names get_opportunity as the follow-up, which distinguishes it from the detail-fetching sibling.

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 extensive operational guidance: scope by country, translate queries per country, use cpv_labels/nuts_names, set status, use type for grants, and expect to filter results yourself. It lacks an explicit 'don't use this when...' statement and mostly implies alternatives rather than comparing against them.

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 burden of behavioral disclosure. It usefully explains that limits include both a current window and non-renewing caps, and implies read-only inspection via 'confirm a setting took.' However, it does not explicitly state that the tool is side-effect-free, how it behaves when no account is connected, or whether it can be called before authentication.

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-loaded: it leads with the tool's purpose, then lists the concrete values returned, then gives explicit invocation triggers. Every sentence contributes useful guidance without repetition or 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?

For a zero-argument inspection tool with no output schema, the description conveys the key return categories (tier, persona, corpus freshness, limit windows) and the situations where it is appropriate. An agent can decide to call it correctly and understand the general shape of the response.

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 and the schema coverage is 100%, so there is nothing for the description to clarify about inputs. The description goes beyond schema constraints by detailing what the returned account context includes, earning the baseline-plus credit.

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 clearly identifies the tool as an introspection call that returns the connected account's tier, persona, corpus freshness, and current limits. This is specific enough to distinguish it from siblings like connect_start, connect_verify, get_workflow, and search_opportunities, which all serve different purposes.

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 explicitly lists when to call the tool: when a user asks about limits, when unsure about authentication status, or to confirm a setting took. It does not explicitly state when not to use it or name alternatives, but the provided triggers are clear and actionable.

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