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

No annotations are provided, so the description carries the full behavioral burden. It clarifies that the response includes full detail and cross-portal links, but does not mention permissions, rate limits, read-only behavior, or whether the cross-portal links are always present.

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 front-loaded sentence with no unnecessary wording. It efficiently conveys the core purpose and the notable inclusion of cross-portal links.

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 is simple with one required parameter, and an output schema exists to explain return values. However, the description does not explain how to obtain or format tender_ref and does not clarify usage relative to sibling tools, leaving some gaps.

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 only repeats that the single required parameter is tender_ref. It does not explain the expected format, source, or example of a tender reference, adding minimal meaning beyond the schema property name.

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 retrieval purpose: full detail for one tender identified by tender_ref, including cross-portal links. It distinguishes the tool from list/search siblings by focusing on a single tender, though it does not explicitly name search_tenders as the alternative.

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 'by tender_ref' implies the tool is used when a known tender reference is available, but there is no explicit guidance on when to use this versus search_tenders or other siblings. No exclusions or 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 supplied, so the description carries the full behavioral burden. 'available' suggests a read-only enumeration, but the description does not explicitly state read-only/non-destructive behavior, permission requirements, or ordering/pagination characteristics.

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?

It is a single short fragment with no wasted words, which keeps it concise. The fragmentary grammar makes it slightly less immediately actionable than a complete sentence, but there is no bloat.

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 no parameters, has an output schema, and is a simple list operation, so the description does not need to explain return values. It establishes the resource and its link to match_profile, but leaves the exact invocation relationship and read-only nature implicit.

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 schema coverage is 100%, so the baseline is 4. There are no parameter semantics for the description to add, and it does not introduce any 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 names the resource ('Names of the company profiles') and ties it to 'match_profile', but it is a noun phrase rather than a verb-led statement of what the tool does. It implies a name-list lookup but does not fully distinguish its purpose from the sibling match_profile 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?

'available to match_profile' implies this is a precursor lookup for match_profile, but the description never explicitly says to call this before match_profile. It also gives no when-not-to-use guidance or alternatives, leaving usage only implied.

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 usefully disclose that results come with reasons and that an unknown profile name triggers a profile-listing response, but it omits that this is a read-only operation, how open_only silently excludes closed tenders, and how max_results truncates the ranking.

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 ranking purpose, with no filler. The second sentence's invalid-input discovery trick is a slightly awkward structure but still earns its place informationally.

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 tool with no annotations, no output schema, and 0% schema coverage on three parameters, the description does not say enough. An agent cannot tell whether results are paginated, what 'reasons' look like, or how open_only and max_results affect the ranking, so it would likely need trial calls to use the 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 description coverage is 0%, so the description must compensate, and it only partially does: it explains profile_name's source (profiles/*.yaml) and its special unknown-name behavior. Neither open_only (which defaults to true and filters results) nor max_results (default 20) is mentioned anywhere, leaving two of three parameters semantically empty.

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?

Uses a specific verb ('Rank') with a specific resource ('tenders') and an explicit scoping input ('a company profile (profiles/*.yaml)'), plus a note that results include reasons. This distinguishes it from search_tenders by intent, though it never names that sibling to make the contrast explicit.

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?

Implied usage is clear from the purpose: call it when you have a named company profile and want ranked tenders. However, there is no guidance on when to prefer search_tenders, and the only explicit tip is an odd discovery hack (pass an unknown name to list profiles) even though a dedicated list_company_profiles sibling exists — the description never points to it.

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. It usefully discloses the governance/refusal model and that errors are self-correcting, which is real value beyond structured fields. It does not state side-effect profile, permission prerequisites, or rate/cost limits, leaving meaningful gaps for a tool with zero annotation coverage.

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?

Four short sentences, front-loaded with the core action, then the exclusivity constraint, then error behavior. Nothing is bloated. The 'only way to aggregate' and 'free SQL does not exist' lines are near-duplicates, costing a little tightness.

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 output schema is present, so return values need no explanation, and the governance framing is well covered. However, with five undocumented parameters at 0% coverage and no annotations, an agent still lacks guidance on how to build a valid metric/filters/dimensions call. Adequate but with a clear structural 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 0% across five parameters, and the description names none of them (metric, filters, dimensions, limit, horizon_days). The pointer to semantic://layer is a partial offset, since metric and dimension names likely live there, but no parameter meaning, format, or default behavior is conveyed in the description itself.

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: 'Run a governed metric from the semantic layer.' The exclusivity claim ('the only way to aggregate') further pins down its role relative to the sibling search/get tools, though it never names those siblings directly. An agent knows what this does without opening the schema.

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?

Explicit routing guidance: this is the only aggregation path, free SQL does not exist, and refused queries surface corrective GovernanceError messages. It tells the agent when to reach for this tool and what to do on failure. It stops short of saying which sibling to use for non-aggregate retrieval, so a 4 rather than a 5.

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 supplied, so the description carries the full behavioral burden, yet it says nothing about result ordering/ranking, whether results are paginated or truncated, or what happens when no filters are supplied. It only implies a hard cap of 50 via the max_results arg, which is parameter semantics rather than behavioral context.

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 one-line purpose followed by a compact per-parameter list with zero filler. The docstring 'Args:' framing is slightly code-styled but does not impede comprehension.

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 values need not be explained, and parameters are well covered. What is missing for a six-parameter search tool is behavioral context: how results are ordered, whether result sets are capped or paged beyond max_results, and how this tool relates to its search-adjacent siblings.

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 must compensate, and it largely does: it defines each of the six parameters with real meaning — query is matched against title and description, source enumerates fts/contracts_finder/ted with empty meaning all, country is ISO alpha-2 with an example, cpv_division is a 2-digit division with an example, open_only keys on deadline, and max_results caps at 50. It stops short of stating how source values interact or whether query is required.

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 ('Search tenders') plus the mechanism (keyword and filters), which is enough to distinguish it from get_tender. It does not distinguish it from match_profile or upcoming_deadlines, which are the siblings an agent could plausibly confuse it with.

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 when-to-use or when-not-to-use guidance, and no mention of the sibling alternatives (match_profile for profile-based matching, upcoming_deadlines for deadline-driven retrieval). The agent must infer selection purely from the tool name and parameter list.

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 implies a read-only listing of open tenders but says nothing about pagination, ordering, the default 14-day horizon, how max_results truncates results, or what a 'profile' match actually means. That leaves several behavioral gaps for a query tool with three parameters.

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?

It is a single tight sentence with the core filter front-loaded and no wasted words. The terseness borders on under-specification, but structurally it is efficient.

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 three-parameter query tool with no annotations and no output schema, the description is too thin: it does not explain max_results, defaults, return shape, or how profile scoping interacts with the deadline filter. An agent would have to guess at several invocation details.

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 must compensate. It only clarifies horizon_days and hints at profile_name; max_results is never mentioned, and there is no explanation of units, defaults, or whether profile_name must match an existing profile exactly. Meaning added beyond the bare schema is minimal.

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 (open tenders) and a clear filter condition (deadlines within horizon_days), plus an optional profile scoping. It distinguishes itself reasonably from generic search_tenders by implying a deadline-window view, though it never explicitly names that sibling or contrasts the two.

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 implies a use case (finding tenders closing soon) but gives no explicit when-to-use vs when-not guidance, no mention of when to prefer search_tenders or match_profile, and no prerequisites. The optional profile filter is mentioned but not explained as a usage decision.

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