SheetsData

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

Annotations already cover readOnly/idempotent/non-destructive; the description adds real value beyond them with a cost disclosure ('Costs 5¢ per call'), the vision-AI processing model, and the precondition that image_key must come from a prior read_datasheet response. It does not describe the response shape, though idempotency is confirmed by annotations.

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?

Dense and front-loaded with cost and core action before the routing guidance and example. Every sentence carries information, though the example and the parenthetical field explanations make it slightly longer than strictly necessary.

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, idempotent vision tool with no output schema, the definition covers purpose, cost, precondition, and selection guidance against its main sibling. What it does not state is the shape of the returned answer, which is the only material 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%, so baseline is 3, but the description adds genuine meaning: image_key is described as 'the storage path in the image URL' sourced from read_datasheet, and question is framed as optional with an inline call example. This goes beyond the schema's terse field docs.

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 (reads with vision AI) and resource (datasheet image: graph, package drawing, pin diagram, schematic), and explicitly ties it to read_datasheet output. An agent can distinguish it from read_datasheet without opening either 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?

Explicitly routes: 'For exact electrical values prefer read_datasheet's text tables; use this for what only the picture shows (package dimensions, pin assignments, curve trends, approximate values off a curve).' Both the when and the when-not, plus the named alternative, 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?

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds real behavioral context on top: per-call cost, the 50-line limit, duplicate-MPN quantity aggregation, compact-vs-verbose output forms, and epistemic caveats ('Unknown remains unknown', 'single_source does not prove only one supplier exists'). That caveat is exactly the kind of semantic limit an agent needs and would not get from annotations.

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?

Dense and front-loaded with the cost signal, and nearly every clause carries information. A few clauses ('Uses exact identities, catalogue snapshots and available distributor details') are contextual filler, and the trailing 'No extraction.' is terse to the point of ambiguity.

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 must describe returns, and it does via the compact/verbose distinction. Combined with cost, input limits, identifier semantics and result caveats, an agent has everything needed to call this tool correctly and interpret its output.

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%, so the description must carry the load, and it largely does: it defines what 'mpn' accepts (MPN or LCSC number), how quantities behave (duplicates aggregated), and what 'verbose' changes (compact columns/rows vs returned objects). It does not spell out the qty bounds (1–1e9) already in the schema, but the meaningful semantics are covered.

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 (Check) and resource (BOM lines) and enumerates exactly what is evaluated: lifecycle, stock vs quantity, single-distributor sourcing, datasheet status, stale/missing prices. No sibling is named explicitly, but the enumerated checks and the 'No extraction' note separate it from check_extraction_status, find_parts and compare_parts.

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?

Gives a clear operating context: cost (2¢ per call), a 50-line cap, accepted identifier types (MPN or LCSC number), and duplicate-MPN aggregation. It stops short of naming when to prefer a different sibling or stating exclusions, so it is strong context without 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 cover read-only/safety, but the description goes well beyond: 5¢ per call charge, that a not-yet-extracted part returns status='extracting' and is not charged, and realistic latency estimates (2.5 min median, 6.5 min p90, ~12 min cold GPU). It also discloses the derating screening policy, the 'llm' source_quote provenance, and that a substituted MPN surfaces resolved_as/data_quality_warning.

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?

Cost and purpose are front-loaded and the verdicts are broken into labeled sections, but the middle paragraphs are dense run-on prose that could be tightened. For a tool of this complexity the length is largely earned, though a few sentences carry redundant detail.

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 carries the full burden and does so: it enumerates the returned fields (verdict, margin_pct, derating_pct, derated_limit, limit_type, source_quote, unmatched, temperature_basis, validation_method) and explains the special statuses. An agent has everything needed to interpret results 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 coverage is 100% so the baseline is 3, but the description adds real cross-parameter meaning: which parameters apply to which part type, that efficiency is required for the switching-converter junction estimate, and that power_dissipation covers 'anything else'. It stops short of documenting switching_frequency's role or the derating interaction with every parameter.

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 ('checks your operating conditions against the part's absolute maximum ratings and recommended operating conditions') and names the exact return vocabulary (PASS/WARNING/FAIL/INSUFFICIENT_DATA). It clearly separates itself from siblings by naming analyze_image for SOA analysis and excluding passives with no ratings 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?

Gives explicit when-to-use guidance broken out by part type (converters/LDOs vs MOSFETs vs logic ICs), states the per-call cost, and provides a concrete 'Not for' list with the alternative tool named. Also tells the agent what to pass when a check would otherwise be INSUFFICIENT_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, idempotentHint, and destructiveHint=false, but the description adds substantial context beyond annotations: return fields like current_step and poll_after_seconds, timing distributions (median 2.5 min, 90th percentile 6.5 min, cold start ~12 min), related_ready parts, and the fact that estimates are not deadlines. This is rich behavioral disclosure for a polling 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?

Front-loads the purpose ('Free. Extraction status of 1-20 parts.') and then delivers dense, necessary status, timing, and polling information without filler. Every sentence earns its place given the tool's complexity.

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, but the description explains the return values (current_step, elapsed_seconds, poll_after_seconds, errors, related_ready) and the full status lifecycle with polling guidance. Nothing an agent needs to call and correctly interpret this tool is missing.

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% and the single parameter is fully documented in the schema. The description repeats '1-20 parts' but adds no new syntactic or semantic details about part_numbers beyond what the schema already provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: checks extraction status for 1-20 parts. It distinguishes itself from siblings by naming prefetch_datasheets and request_datasheet_upload as alternatives for specific status outcomes.

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?

Gives explicit polling rules, stop conditions, and a status-to-action mapping that names sibling tools. An agent knows exactly when to keep polling this tool versus when to call read_datasheet, prefetch_datasheets, or request_datasheet_upload.

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 read-only, idempotent, non-destructive, open-world, so the bar is lower; the description still adds real behavioral context beyond them: a 2¢ per-call cost, the all-or-nothing rejection of non-MPN inputs, the error column for valid-but-unknown MPNs, the resolved_as flag when a lookup lands on a different MPN, and the fact that it never itself starts extraction.

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?

Long but front-loaded: cost, then what it does, then the return shape, then the routing table, then the compact/mode behavior. Nearly every clause is actionable, though the routing enumeration is dense enough that it could be tightened without losing 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?

No output schema exists, yet the description fully characterizes the return payload (per-provider specs, price breaks and links, cached datasheet summary, a parameters × parts table, and per-part lifecycle/stock/datasheet_status/resolved_as flags) plus the mode variants, so an agent knows both when and what to expect.

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 baseline is 3; however the description adds meaning the schema does not, notably that include_summaries only applies with compact=true and that compact mode still retains the flags and comparison table. It restates the 2-5 bound and the 'not a value/reference designator' constraint that the schema already gives, so it does not reach 5.

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 ('Compares 2-5 parts ... side by side in one call') and explicitly scopes it to parts you already know, naming search_parts and find_alternative as the candidate-discovery siblings. An agent can distinguish this from every sibling without opening a 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?

Gives explicit when-to-use and prerequisites: find candidates with search_parts/find_alternative first, prefetch_datasheets before expecting summaries. It also routes on results (datasheet_status 'ready' → read it; 'extracting' → poll check_extraction_status; 'not_extracted' → prefetch_datasheets; 'no_source' → request_datasheet_upload), which is unusually actionable.

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?

Goes well past the annotations: discloses the 10¢ fee and that it is only charged on success, the server-side validation sequence (re-hash, PDF check, MPN-on-page-1 check), private-library insertion, extraction queueing, latency distribution (2.5/6.5/12 min), and the full failure taxonomy with per-error remediation. The destructiveHint/openWorldHint flags are consistent with this write-plus-fee operation.

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?

Dense but organized: fee, precondition, server behavior, return values, timing, then failures are ordered logically, and the failure list is packed with recovery hints. Slightly long and header-less, but no sentence is 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?

With no output schema, the description carries the burden and delivers: it enumerates returned fields (document_id, mpn, sha256, file_size_bytes, status='pending'), the success/failure split, billing semantics, and expected latency. Nothing material for correct invocation is missing.

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% for a single parameter, so the schema already documents upload_token as an opaque token from request_datasheet_upload. The description restates the same provenance and adds no format, length, or expiry semantics beyond what the schema carries.

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 ('Confirms an upload') with an explicit pointer to the producing sibling (request_datasheet_upload) and the downstream poll target (check_extraction_status). An agent can place this tool in the workflow without opening any 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?

States the precondition ('an upload started with request_datasheet_upload'), the required handoff value ('pass its upload_token'), and the follow-up action ('poll check_extraction_status with the MPN'). Both when-to-use and the next step are explicit.

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?

Goes well beyond the readOnly/openWorld/idempotent annotations: it discloses the 2¢ per-call cost, that constraints are never relaxed silently, that failures surface in removed_by_constraints/relaxed_matches, that not_found is not charged, and that match_score is similarity not verified compatibility. This is exactly the behavioral context an agent needs before invoking.

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 with cost and purpose, and nearly every sentence earns its place. It is dense and slightly sprawling toward the end (datasheet_status branching plus a pointer to server instructions), which keeps it just below a perfect score.

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 carries the return-shape burden and does so fully: match_score/match_notes, lifecycle/stock/datasheet_status, removed_by_constraints, relaxed_matches, and the not_found error with matches_without_constraints. An agent has everything required to call and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, but the description adds real meaning beyond it: fuzzy package equivalence examples (SOT-23 ≡ SOT23, SOIC-8 ≡ SOP-8), the non-silent-relaxation semantics of constraints, and the compact/include_original_summary interaction ('leaves out the reference part's summary unless include_original_summary=true').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource with the triggering conditions: 'Finds alternative and second-source parts for an MPN that is out of stock, end of life or too expensive.' It also explicitly differentiates from the sibling compare_parts ('for a head-to-head of candidates you already have, use compare_parts').

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?

Names when to use it (out of stock, EOL, too expensive) and routes to the alternative tool compare_parts for a different need. It even documents the downstream branching per datasheet_status, telling the agent which sibling to call next.

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

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

Annotations already cover readOnly/idempotent/openWorld safety, and the description adds real behavioral context on top: evidence ranking semantics (pass/fail/unknown, unknown = unverified), source and test-condition retention, compact-vs-verbose return shape, 'Free' cost signal, and the DigiKey/JLCPCB configuration dependency. This is meaningful disclosure beyond the structured fields.

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 with the cheapest useful fact ('Free') followed by the core action, and every sentence carries distinct information about constraints, ranking, or output format. It is dense and the inline example fattens the prose, but nothing is truly 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 6-parameter filtering tool with no output schema, the description covers result ranking, evidence reliability, and return shape (compact vs verbose), which is what the agent most needs. Remaining gaps are minor: limit/pagination behavior and package filtering semantics are left to the schema defaults.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 33% schema coverage, the description compensates well: it shows the constraints object shape via example, clarifies value format ('24 V', '10 mΩ'), mentions text operators like 'contains', and explains verbose toggles output objects vs compact rows. It omits semantics for limit (1-20, default 5) and leaves package unelaborated, so not quite a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Find candidates by function and numeric specs') plus scope modifiers (units, package, stock) that differentiate it from a plain keyword lookup. It implicitly separates itself from check_design_fit via 'Does not validate design fit,' but never names search_parts or find_alternative, so sibling differentiation is incomplete.

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?

Provides a concrete usage example with query + constraints, explains what parameter naming schemes are accepted (vds, rds_on, canonical names, text constraints), and states a clear when-not boundary ('Does not validate design fit'). It stops short of routing the agent to alternatives like search_parts or find_alternative, so it is not a full 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?

Goes well beyond the readOnly/openWorld annotations: it discloses cost behavior ('Free', prefetch at no extra charge), that resolved_as/data_quality_warning flag MPN mismatches, that lifecycle_warning marks risks, and cautions that absence of errata_sections does not prove absence of manufacturer errata. This is unusually rich behavioral context, though it leaves the return shape itself partly implicit.

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 routing guidance is front-loaded and valuable, but the body is a dense run-on paragraph with nested parentheticals (e.g. the read_datasheet / read_args aside) that is hard to scan. Much earns its place, but the structure could be broken into clearer segments.

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 5-parameter read tool with no output schema and heavy cross-tool interplay, the description covers purpose, cost, edge cases, warning fields, and downstream routing comprehensively. An agent has everything needed to call it and interpret the result 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 the schema already documents all five parameters including compact, verbose, provider and prefetch_datasheet. The description mostly restates these (e.g. family_summary for compact, 'no extra charge' for prefetch), adding little interpretation beyond what the schema provides.

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 and enumerates exactly what the response contains (provider specs, price, stock, lifecycle, specialized_specs, datasheet_summary, datasheet_status, errata_sections). It is clearly distinguishable from siblings like search_parts, read_datasheet and check_extraction_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use after search_parts to drill into one result', and provides a complete decision table mapping datasheet_status values ('ready', 'extracting', 'not_extracted', 'no_source') to the specific sibling tool to call next. When-to-use and alternatives are fully specified.

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 only declare the safety profile (readOnly/non-destructive), but the description adds substantial behavior beyond them: it is free, returns immediately with per-part status, median/p90/cold-start latency estimates framed as non-deadlines, a Free-plan daily cap surfaced as 'trial_limit', and the non-obvious lifecycle of 'queued' → 'resolving' → final 'no_source'. This is exactly the context annotations cannot carry.

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 with cost and effect, then timing, then status routing. Dense and nearly every sentence earns its place, though the status-to-action mapping reads as a compressed run-on and could be split for scanability.

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 must explain returns, and it does: every status value is enumerated with the follow-up action for each, and the polling tool is named. An agent has everything needed to call it and act on the result.

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 schema already documents the MPN/LCSC-vs-value distinction, so baseline is 3. The description adds real meaning on top: the BOM-scale use case, the value-only-row exception routed to search_parts, and a concrete example call with sample identifiers.

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 first sentence states a specific verb and resource ('Starts background extraction for ... parts') plus scope (up to 20 at once) and the motivating scenario (a BOM). It is immediately distinguishable from siblings like read_datasheet and check_extraction_status, which the description names.

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 when-to-use ('so they are ready before you read them'), when-not/input constraints ('MPNs or LCSC numbers only'), and a full alternative-routing map: poll check_extraction_status, resolve value-only rows with search_parts, attach PDFs via request_datasheet_upload for 'no_source'.

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 only declare readOnly/openWorld/non-destructive; the description adds real behavioral context the annotations cannot: 2¢ per call cost, that the first extraction read is not charged, and concrete latency estimates (2.5 min median, ~12 min cold GPU). It also warns that microcontroller register detail may live in a separate reference manual. Only minor gap: no explicit statement about auth or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with cost and the core section-mode workflow, then search mode, then status routing. Long but dense and largely waste-free; the status-mapping sentence is a slight compression win but adds length rather than cutting it.

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 an 8-parameter, no-output-schema tool, the description covers mode selection, paging, cost, latency, failure states, and sibling routing – everything an agent needs to call it correctly and interpret the result.

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% (baseline 3), but the description still adds non-duplicative meaning: section names derive from the datasheet's own slugified headings, unknown names return nearest sections and pages, and next_offset/max_chars are framed as a paging workflow. This goes beyond the schema's field-level text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Reads a part's datasheet') and immediately distinguishes its two operating modes (section vs. search) with concrete examples of section names and queries. An agent can identify what this tool 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?

Explicitly routes the agent: start with section='summary', prefer named sections over 'all' which 'can fill your context', and maps each datasheet_status value to the correct alternative sibling (check_extraction_status, prefetch_datasheets, request_datasheet_upload). This is a full when/when-not/alternative map.

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 only declare it is a write with no destruction; the description adds substantial non-obvious behavior: it is free but the fee is charged at confirm, validation rules (parseable PDF, declared hash/size, MPN on first page, image-only PDFs fail), 50 MB limit, org-private results, and 15-minute token expiry.

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 with the key cost fact ('Free.') and organized as a numbered three-step flow, so structure is strong. It is long and slightly repetitive (fee and checks restated), which keeps it from a 5, but almost every sentence carries actionable 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?

There is no output schema, yet the description enumerates the returned fields (upload_url, upload_method, upload_headers, upload_token) and the full two-step follow-through, so an agent has everything needed to complete the workflow.

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 already 100%, so the baseline is 3, but the description adds real meaning by explaining what the SHA-256 and byte size are checked against at confirm time and by clarifying the MPN-or-stem matching rule on page one. It does not add syntactic detail beyond the schema's examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: obtaining a signed URL to upload a datasheet PDF. It clearly distinguishes itself from siblings by naming confirm_datasheet_upload as the follow-up and by scoping to cases where the datasheet is absent.

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?

Gives explicit trigger conditions (datasheet_status 'no_source' after search completes, or 'unsupported'), an explicit exclusion (not while 'resolving'), and routes the agent to confirm_datasheet_upload as the required next step. Nothing is left to inference.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, non-destructive), but the description adds genuinely new operational facts: a 2¢ per-call cost and the shape of the return ('matching chunks with part_number and a 0-100 relevance_score'). It does not discuss empty-result behavior or how limit affects result quality, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, all front-loaded: cost first, then scope, then return shape, then the alternative. Every sentence carries a distinct fact and none restates the name or 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?

There is no output schema, yet the description still supplies the return shape and relevance scale, plus corpus scope, cost, and the disambiguation rule. An agent has everything needed to decide between this and search_parts and to interpret 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds real meaning for the required query parameter by showing the expected style (spec-based natural-language phrase rather than a part number). The limit and section_type parameters are left entirely to 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 (semantic search) and resource (extracted datasheets) and immediately bounds the corpus with 'not every part that exists'. It also names the sibling it is not: search_parts for lookup by part number, so an agent can distinguish it without opening either 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?

Gives the positive trigger with a concrete example ('low-noise LDO with PSRR above 70dB') and an explicit when-not rule routing part-number lookups to search_parts. Both the condition and the alternative are named, leaving nothing 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 cover safety (readOnly, idempotent, openWorld, non-destructive), but the description adds substantial behavior the annotations cannot: queries run in parallel across three providers, results are merged by MPN, eval boards/kits are split out as related_kits for MPN queries, and private-library matches are appended with source='private_library'. That is exactly the kind of pre-call context an agent needs.

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 with the cheapest signal ('Free. Start here.') and then builds from core behavior to return shape to routing. The datasheet_status mapping is dense but each mapping earns its place; the trailing 'Full list in the server instructions' is the only mild redundancy.

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 carries the full burden, describing merged-by-MPN results with per-source price and stock, datasheet_status, related_kits and private_library entries with tags. Combined with the status-to-tool routing table, an agent has everything needed to call it and act on 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?

Schema description coverage is 100%, with limit, query and providers all documented including the 3× multiplier caveat for providers='all'. The description adds no syntax or format detail beyond that, so the baseline 3 applies; it does implicitly hint that private-library results are appended regardless of the provider selection.

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 ('Searches components by part number or keyword') plus the exact scope (JLCPCB, Mouser, DigiKey, in parallel). It explicitly contrasts itself with the closest sibling: 'For spec-based discovery in plain language, use search_datasheets,' so an agent can route without opening any 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?

'Free. Start here.' gives an explicit entry-point recommendation, and the description names the alternative (search_datasheets) with the condition that selects it (spec-based plain-language discovery). It further routes downstream work: poll check_extraction_status, prefetch_datasheets, request_datasheet_upload, each keyed to a concrete datasheet_status value.

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