Touchline Wire — FPL & Premier League Intelligence

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 behaviour is covered. The description adds value by naming the exact per-player data returned, but says nothing about edge behaviour: unknown/unmatched player names, ambiguous names, partial results, or which Gameweek is used when 'upcoming' is ambiguous.

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?

One front-loaded sentence with no filler — the purpose comes first and the return-field list follows. It is dense but every clause carries information about what the agent gets back.

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 only one fully documented parameter, the description's enumeration of returned fields (price, ownership, Start %, fixture, set-piece role, injury status, suspension risk) is exactly the missing piece an agent needs. Remaining gaps are minor behavioural edge cases rather than blockers.

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 described with examples, so the baseline is 3. The description only restates that the input is a list of player names; it adds no format rules, matching semantics, or batch-size limits beyond the schema.

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 ('Audit') and resource ('list of FPL player names') scoped to an upcoming Gameweek, and enumerates the per-player outputs, so an agent can tell this is a bulk player-lookup/enrichment tool. It does not explicitly distinguish itself from overlapping siblings such as get_injuries_and_suspensions or get_set_piece_takers, which keep it from 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 implied: auditing a squad list ahead of a Gameweek. There is no explicit when-to-use/when-not-to-use guidance and no pointer to alternatives when only one facet (e.g. injuries or set-piece takers) is needed. An agent must infer selection from the field 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?

Annotations already declare readOnly, idempotent, non-destructive behavior, so safety needs no restating. The description contributes that the result covers all 20 clubs and includes confidence scores plus predicted formations, which is useful payload context, but says nothing about refresh timing or what is returned when predictions are unavailable.

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 front-loaded sentence with no filler, hedging, or repetition. Scope (all 20, current gameweek) and payload (formations, XIs, confidence) are both packed in without waste.

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 no-parameter, read-only tool with no output schema, the description covers the essentials: what comes back and for which gameweek. The remaining gap is behavioral edge cases (stale or missing predictions), which is minor at this complexity level.

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 takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate about inputs, and it correctly avoids inventing any.

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?

"Retrieve the complete slate of all 20 Premier League predicted formations, starting XIs, and confidence scores" names a specific verb, resource, and payload. The "all 20" scope implicitly separates it from the singular sibling get_predicted_lineup, but it never names that sibling, so the differentiation is inferred rather than stated.

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 "for the current 2026/27 Gameweek" gives an implicit trigger condition (use when you need the whole slate for the live gameweek). However, it offers no explicit when-not guidance and does not tell the agent to prefer get_predicted_lineup when only one team is of interest.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one behavioral detail — that angles are 'RoboKlopp starter-filtered' — but says nothing about how the limit applies across multiple leaderboards or how club/match filters interact, which are the meaningful behavioral unknowns for a read tool.

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 front-loaded sentence with a clear verb and resource first, and no filler or restated name. It is dense with domain jargon (Foul Magnets/90, Poisson 1+ & 2+, BTTS) but every phrase maps to actual returned content, so little 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?

There is no output schema, and the description compensates by enumerating the categories of data returned, which is the right move for a read-only stats tool whose annotations are complete. What remains missing — pagination/limit behavior and how filters combine — is minor for a tool with zero required parameters.

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 the schema already documents all four parameters including the enum. The description reinforces the meaning of the categories by mapping them to the stat families listed (shots on target, fouls, magnets, corners), which adds mild value, but it does not clarify whether 'limit' applies per leaderboard or overall, nor how club vs match combine.

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 ('Retrieve') and names the exact resource and season ('2026/27 Premier League Bet Builder cheat-sheet stats'), then enumerates the stat families returned. An agent can tell it is a stats-lookup tool, though it never explicitly distinguishes itself from sibling tools like get_player_props or get_set_piece_takers that cover overlapping player-level data.

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 by the content list: an agent can infer this is for bet-builder angle research, but there is no explicit statement of when to choose it over get_player_props or get_match_preview, and no exclusions or prerequisites. Guidance is adequate but entirely inferential.

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 cover safety and idempotency: readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds useful behavioral context by stating that the tool returns all 20 clubs, that the data is 'verified' and scoped to 2026/27, and which fields are included, though it does not describe refresh cadence or formatting.

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 filler. It states the core action, scope, season, and returned attributes efficiently.

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, read-only directory tool with no parameters and no output schema, the description is complete enough. It specifies the number of records, the season, and the fields returned, giving the agent what it needs to decide whether to call the tool.

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 is empty, so there are no parameter semantics to explain. The baseline for a zero-parameter tool is 4, and the description does not need to add parameter 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 description uses a specific verb and resource: 'List all 20 Premier League clubs.' It names the season and the exact attributes returned, so the agent can distinguish this directory tool from statistical or lineup-focused siblings.

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 implied by the tool name and the phrase 'List all 20 Premier League clubs,' but the description does not explicitly state when to use this tool versus siblings. It also does not address the overlap with get_set_piece_takers despite including 'set-piece specialists' in the returned fields.

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, closed-world behavior, so the safety profile is fully covered. The description adds only the FDR 1-5 scale convention; it says nothing about how rankings are computed, whether blank/single-club results differ, or what the response looks like.

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 front-loaded sentence fragment with no filler; the key noun (FDR) and scale appear immediately. The phrasing is slightly garbled ("upcoming ... ticker"), which costs a point but not usability.

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, zero-required-parameter, read-only ranking tool with full schema coverage and no output schema, the definition conveys enough to call it correctly. The only gap is that the return shape (per-gameweek ratings vs. a single aggregate per club) is left unstated.

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%, with each of club, sort, and window documented including enum values and defaults, so the schema carries the load. The description contributes no additional meaning such as how the club filter interacts with sort or what a 1-10 gameweek window means for the ranking.

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 ("Rank") and resource (Premier League clubs) plus the metric being ranked (upcoming FDR 1-5). An agent can tell this is a difficulty-ranking view rather than raw fixtures, but it doesn't explicitly distinguish itself from get_fixtures or get_table.

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: an agent infers this is for spotting which clubs have the easiest/hardest upcoming run. There is no explicit when-to-use, when-not, or pointer to alternatives such as get_fixtures for actual match-level detail.

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 declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description adds the scope constraint ("upcoming") and the shape of the returned data fields, but says nothing about result limits, pagination, sort order, or how far ahead the fixture window extends.

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 sentence, front-loaded with the verb and resource, with the returned data enumerated in a compact parenthetical. No filler, no redundancy with the title.

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, read-only, zero-required-parameter list tool with no output schema and complete annotation coverage, the description covers purpose and return fields adequately. The only meaningful gap is the absence of any statement about result volume, ordering, or the time horizon of "upcoming" fixtures.

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 both optional filters (club, gameweek 1-38) are already documented in the schema, which sets the baseline at 3. The description adds nothing about filtering behavior, and its mention of "Gameweek numbers" refers to returned values rather than the gameweek filter, so it does not deepen parameter meaning.

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 pairs a specific verb ("Retrieve") with a specific resource ("upcoming 2026/27 Premier League matchday fixtures") and even enumerates the returned fields (UTC kickoff timestamps, Gameweek numbers, home/away pairings). That is enough to separate it from per-match siblings like get_match_preview and get_match_report, though those siblings are never named explicitly.

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 word "upcoming" implies a forward-looking window and thus implicitly excludes historical results, which is useful. However, there is no explicit when-to-use vs when-not-to-use guidance and no routing to related siblings such as get_fixture_difficulty or get_match_preview, so the agent must infer the boundary.

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, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered and the description cannot earn credit there. The description does add genuinely useful context beyond the annotations: the data is 'live' and scoped to the 2026/27 season, and the exact content sections are listed. It does not say anything about freshness/caching, response format, or size, so it sits at an adequate rather than rich level.

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?

One front-loaded sentence with the action and resource first, then the content breakdown. Every listed item is informative content rather than filler, though the enumeration is dense enough to read somewhat like keyword stacking.

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 one optional, fully documented parameter and annotations covering safety and world-boundness, the remaining burden is describing what comes back, and the description does enumerate the briefing's sections in place of a missing output schema. Minor gaps remain around response format and freshness, but nothing an agent needs in order to call it correctly is absent.

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?

There is a single optional parameter with 100% schema description coverage, which already explains the 1-38 range and the default to the next active planning Gameweek. The description adds no further meaning about the gameweek parameter, so the baseline of 3 for fully documented schemas 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 uses a specific verb ('Retrieve') plus a named resource ('Touchline Wire's live 2026/27 FPL Gameweek briefing') and enumerates the exact sections returned (captaincy matrix, differentials, enablers, risers/fallers, yellow-card tightropes, injury flags). An agent knows precisely what the tool produces. However, it never distinguishes itself from overlapping siblings such as get_fpl_transfer_trends, get_fpl_picks, or get_injuries_and_suspensions, which cover pieces of the same content.

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 word 'Gameweek' plus the enumerated planning content signals this is a weekly FPL planning digest, and the schema note about defaulting to the 'next active FPL planning Gameweek' reinforces that. There is no explicit statement of when to call this versus the several sibling tools that surface transfer trends, picks, or injury data.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds little beyond that — it does not say results are ranked, how ranking is determined, or whether modes alter ordering, and it omits pagination/limit behavior that the schema only partly covers.

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 front-loaded sentence that lists the filter surface without filler, which is efficient for a filter tool. It is slightly over-packed in one clause, 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 read-only, 7-parameter, fully documented filter tool this is close to adequate, but with no output schema the description should at least sketch the return shape (ranked player picks with which fields) and the default ranking/limit behavior. Those gaps leave the agent guessing about result ordering.

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 every parameter already carries its own explanation with examples and ranges; the description merely restates the same filter names. It adds no new semantics such as how min_start_pct interacts with mode presets or whether filters compose with AND logic.

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 pair ('Search and filter') plus a concrete resource ('2026/27 Premier League FPL players') and enumerates the dimensions being filtered, so an agent immediately knows what the tool returns. It does not, however, distinguish itself from close siblings such as audit_fpl_players or get_fpl_transfer_trends, which also deal with player lists.

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 mode presets (differentials, value, captaincy, all) hint at when this tool is appropriate, but the description never states when to prefer it over sibling tools or what happens if no filters are supplied. There are no exclusions or alternative-tool routing.

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, so the safety profile is covered structurally. The description adds that data is 'live' and names the trap-alert categories, but says nothing about freshness/caching, which gameweek is assumed (current?), or return shape for a tool with no output schema.

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 dense sentence, front-loaded with the core resource and followed by the supporting data bundle; no filler clauses. It is jargon-heavy ('RoboKlopp Start %', '4-YC trap alerts'), which is acceptable domain vocabulary but assumes familiarity.

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 only two optional parameters and no output schema, the description does a fair job of naming the returned data components. However, it leaves the gameweek scoping implicit and does not resolve overlap with adjacent tools (transfer rumours, injuries/suspensions), which an agent needs in order to choose 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 100%, so both 'limit' and 'direction' are fully documented in the schema, making 3 the baseline. The description's mention of 'price risers/fallers' and 'most transferred in/out' loosely echoes the direction enum values but adds no defaulting, paging, or sorting semantics beyond the schema.

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 ('Retrieve') and a well-defined resource ('live FPL Gameweek transfer momentum'), then enumerates what it covers (transferred in/out, net delta, price risers/fallers, Start %, trap alerts). It does not differentiate itself from the sibling 'get_transfer_rumours', which an agent could plausibly confuse with FPL transfer momentum data.

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: an agent can infer this is for checking gameweek transfer momentum and bandwagon traps. There is no explicit 'use this when...' statement, no exclusion of alternatives such as get_transfer_rumours (real-world rumours) or get_injuries_and_suspensions (which overlaps with the injury trap alerts mentioned).

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, so the safety profile is covered. The description adds that data is 'live' for the current 2026/27 season, which is useful freshness context, but says nothing about update cadence, snapshot vs. history, or whether all clubs are returned by default.

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?

One front-loaded sentence that enumerates the four content categories with zero filler. Every clause earns its place by distinguishing injury, medical, ban, and suspension-tightrope data.

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-param, read-only tool with rich annotations and no output schema, the description covers what data comes back and for which season. The only gap is default unfiltered behavior (all clubs vs. none), which is minor.

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 single optional 'club' filter is fully documented as a name or slug. The description never mentions the filter, so it adds no meaning beyond the schema; 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?

Specific verb ('Retrieve') plus a precisely scoped resource: live 2026/27 Premier League injuries, medical return dates, red/cup bans, and FA 4-yellow-card suspension tightropes. No sibling tool covers availability, so the agent can route here without ambiguity.

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 by the domain ('injuries, bans, suspensions') — there is no explicit when-to-use statement, no mention of when to prefer get_predicted_lineup or audit_fpl_players instead, and no note that the result is a league-wide snapshot unless filtered. Adequate for a single-purpose tool but leaves routing 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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful behavior the annotations do not: it is scoped to upcoming 2026/27 fixtures and it discloses the four content blocks returned, which matters because there is no output schema.

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?

One sentence, front-loaded with the verb and scope, with the returned sections listed compactly after the colon. Nothing is redundant or 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?

With only two fully documented parameters and no output schema, the description supplies the missing return-value picture by naming the four intelligence sections. Minor gap: it does not say what happens when no upcoming fixture exists between the two clubs.

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 both parameters carry examples of accepted name/slug forms, so the schema already does the work. The description adds only the notion that the pair identifies an upcoming fixture, with no extra guidance on ambiguous or cross-competition club names.

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 gives a specific verb ('Retrieve') plus a specific resource ('pre-match tactical intelligence for an upcoming 2026/27 fixture') and enumerates the payload: formation clash, manager matchup, squad availability, form guide. That clearly separates it from get_match_report (post-match) and get_predicted_lineup (single-team lineup), though it never names those siblings explicitly.

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 word 'upcoming' implies this is the pre-match tool, which is real usage signal, but there is no explicit when-to-use/when-not statement and no routing to get_match_report, get_predicted_lineup, or get_fixtures. An agent must infer the boundary from sibling names alone.

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 this a safe, idempotent, closed-world read, so the safety profile is covered. The description adds value by disclosing the report payload (confirmed lineups, timelines, xG, possession), but says nothing about behavior when both optional params are omitted, when both are supplied, or what happens for an unplayed fixture.

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 dense sentence that front-loads the verb and resource and then lists the payload. No filler, no restatement of the title.

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, the description correctly carries the burden of describing return contents comprehensively. The remaining gap is the absence of any note on how the two optional selectors interact, which matters for a tool requiring zero parameters.

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 both parameters are already documented with examples and semantics. The description adds no further meaning about arguments, so the baseline of 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?

Uses a specific verb ("Retrieve") plus a well-scoped resource ("post-match tactical reports") and enumerates the contents. "Post-match" implicitly contrasts it with get_match_preview, but no sibling is named explicitly.

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 "post-match" framing implies the tool is for completed matches rather than upcoming ones, which is usable context. However, nothing tells the agent how to choose between get_match_preview, get_all_lineups, or this tool, and there is no guidance on the club vs fixture_id selection.

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, destructiveHint=false and a closed-world source, so the safety profile is covered. The description adds genuine context beyond that: the season (2026/27), the upstream provider, and the per-90 normalization basis. It says nothing about default scope when no club is supplied, result ordering direction, or volume/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?

A single front-loaded sentence that puts the verb, season, source and normalization before the metric parenthetical. Efficient and free of filler, though the parenthetical list is dense and could be trimmed since the schema enumerates the sort options.

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 only two optional parameters and full annotations, the definition is close to sufficient, but there is no output schema and the description never states the shape of the 'raw telemetry' payload, the default behavior with no club filter, or ranking direction. Those gaps are modest rather than fatal.

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 both optional parameters ('club' and the 'sort' enum) are already fully documented, making 3 the baseline. The description's metric list adds light meaning by mapping the per-90 families to the sort concepts, but it omits 'goals' and 'Total Shots' fidelity against the enum values, so it does not extend the schema materially.

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?

Names a specific verb ('Retrieve') and a precisely scoped resource: raw 2026/27 API-Sports Pro per-90 player prop telemetry, with the five metric families enumerated. An agent knows exactly what data comes back, though the description never contrasts it with plausible siblings like get_bet_builder_stats or audit_fpl_players.

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 statement of when to reach for this tool versus the player-stat siblings, and no prerequisites or exclusions. The metric list implies a per-90 telemetry use case, but selection between this and get_bet_builder_stats is left entirely 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?

The annotations already establish read-only, idempotent, non-destructive behavior, so the description's main added value is disclosing that these are AI predictions and listing the returned elements: Starting 11, formation, starter likelihoods, bench options, and manager notes. It does not discuss freshness, model limitations, or reliability, which would have made it richer.

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 filler. Each phrase contributes either the tool's action, the prediction source, or the returned content.

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, one-parameter tool with no output schema and strong safety annotations, the description is largely complete because it enumerates the key returned fields. It could be improved by clarifying its relationship to get_all_lineups and by noting prediction freshness or limitations.

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 single club parameter is fully documented in the schema with name/slug examples. The description adds a useful constraint that the club should be a 2026/27 Premier League club, but it does not add slug normalization or other format details beyond the schema.

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 gets the RoboKlopp AI predicted Starting 11 and related output for a Premier League club. It clearly states the returned content, though it does not explicitly distinguish this single-club tool from the sibling get_all_lineups.

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 'for a 2026/27 Premier League club' gives useful scope, but the description does not say when to use this tool instead of get_all_lineups, get_match_preview, or other lineup-adjacent siblings. Usage is therefore implied rather than explicitly guided.

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, so the safety profile is covered. The description usefully adds that the dataset is season-specific (2026/27) and limited to Select Group 1 Premier League referees, but says nothing about data freshness, pagination, or what a dossier response contains.

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?

One sentence, front-loaded with the verb and scope, and the metric list is packed efficiently. Nothing is redundant or padded.

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-optional-parameter read tool with no output schema, the description covers the dataset, the population, and the returned metrics adequately. A note on whether results are per-season aggregates versus per-match breakdowns would make it 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% and the single 'referee' slug parameter is fully documented in the schema, including the omit-to-return-all behavior. The description adds no extra parameter meaning, so the baseline of 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 pairs a specific verb ('Retrieve') with a precisely scoped resource ('2026/27 PGMOL Select Group 1 Premier League referee statistical dossiers') and enumerates the metrics contained (strictness index, cards per match, fouls, penalty rates). No sibling tool covers referees, so differentiation is implicit rather than stated, which keeps it just 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?

There is no when-to-use guidance, no mention of alternatives, and no prerequisites or exclusions. The agent must infer from the metric list that this is for officiating-tendency analysis rather than, say, general match lookup.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: results are 'verified', season-scoped to 2026/27, and returned as ranked 1st/2nd choice per set-piece type — useful given no output schema. It says nothing about freshness or refresh cadence, which keeps it below 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?

A single sentence with the resource and its dimensions front-loaded and no filler wording. Every phrase (verified, 1st/2nd choice, the three set-piece types, season, league) 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?

For a simple read-only tool with one optional parameter and no output schema, the description conveys enough about the returned content (ranked takers by set-piece category, per club) to call it correctly. Response structure details such as per-club nesting or field names are left unspecified.

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 optional `club` parameter is fully documented including the omit-to-return-all default. The description adds no parameter meaning beyond that, so the baseline of 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 states a specific verb and resource ('Retrieve ... takers') and scopes it precisely to penalties, corners, and direct free-kicks with 1st/2nd choice ordering for 2026/27 Premier League clubs. It is distinguishable from every sibling (lineups, injuries, props, fixtures), though it does not explicitly name an alternative or non-overlap boundary.

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?

No explicit when-to-use, when-not-to-use, or alternative is given; the domain implies usage (e.g., FPL or preview prep where set-piece duty matters). The only routing guidance, that omitting the club returns all 20, lives in the schema rather than the description.

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, so the safety profile is fully covered. The description adds only mild context ('official', '36-team' implying the full table with one row per club); it does not mention ranking criteria, tiebreakers, or whether the table is live vs. snapshot.

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 front-loaded sentence with no filler; the resource and its scope are stated immediately and 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 simple single-parameter read tool with full annotation coverage and no output schema, the description is essentially complete. Minor room remains: it doesn't say what the table contains (position, points, goal difference) or whether the 2026/27 season data is current.

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% with an enum that already documents 'epl' and 'ucl' meanings. The description restates the same competition mapping without adding format, default-behavior, or error-handling detail beyond the schema, so the baseline of 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 ('Retrieve') and resource ('official 2026/27 ... standings') and names the exact two competitions covered. It is unambiguous what the tool returns, though it does not explicitly distinguish itself from sibling tools such as get_fixtures or get_clubs.

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 implies usage (fetch league or UCL standings) and the schema default of 'epl' hints at the common case, but it offers no explicit when-to-use/when-not guidance or pointer to alternative sibling tools for related data.

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=true, idempotent=true, openWorld=false, destructive=false, so the safety profile is fully covered. The description adds useful data semantics — freshness ('live') and that results carry a 1-4 journalistic reliability grade — but says nothing about result volume, empty/no-rumour behavior, or coverage 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?

A single front-loaded sentence with no filler; the resource and grading scheme come first. It is efficient, though quite terse for a tool with two filter dimensions.

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 is the only place return shape could be described — it does not say what a rumour record contains (club, player, source, tier, date). For a low-complexity read-only fetch this is acceptable but leaves a real 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% and both parameters are documented in the schema, including the enum and its direction (1 = highest reliability). The description reinforces the tier concept but adds no syntax or semantics beyond that, 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?

Specific verb+resource+scope: 'Retrieve live 2026/27 Premier League transfer and managerial rumours graded Tier 1-4 by journalistic reliability.' The tier-grading qualifier helps separate it from get_fpl_transfer_trends, but the description never names that sibling, so the differentiation is left for the agent to infer.

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 by 'live' rumours and the optional filters; there is no explicit when-to-use, when-not-to-use, or alternative named (e.g. get_fpl_transfer_trends for FPL-side movement). An agent can pick this tool for a rumours query, but must reason about edge cases itself.

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