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

Annotations already cover readOnly/openWorld, and the description adds genuinely non-obvious behavior: values are passed through unchanged in SEC order, taxonomy/concept are case-sensitive and syntax-checked only, missing concepts surface as NOT_FOUND, and precision loss is handled by emitting the SEC's text with a numbers_as_text index. That is substantial disclosure beyond the annotations, though nothing is said about pagination or size limits for large concepts.

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 core statement, then three short paragraphs each covering a distinct behavior. Every sentence carries information; the only mild cost is that the parenthetical syntax note and the precision note are dense without examples.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be explained, and the mutation/safety profile is covered by annotations. Still missing for a 3-required-parameter XBRL tool: what a valid taxonomy looks like, how cik_or_ticker is resolved, and any hint about response size for concepts with many observations.

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 parameter meaning; it does so well for taxonomy and concept (verbatim insertion into the SEC address, case sensitivity, syntax-only validation) but says nothing about cik_or_ticker beyond the name, and gives no examples of valid taxonomy values.

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

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

The description names a specific resource — the SEC companyconcept document for one company and one concept — and states the scope ('every unit and every observation, in the SEC's order'), which is enough to distinguish it from get_companyfacts (all concepts for a company) in practice. It never names that sibling explicitly, so the differentiation is implicit 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?

There is no when-to-use guidance and no routing to alternatives such as get_companyfacts or get_frames, despite those siblings covering adjacent XBRL retrieval. The only conditional mentioned is an error outcome ('A concept the company never reported is NOT_FOUND'), which is behavior, not usage guidance.

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 and openWorld, but the description adds real behavioral detail beyond them: values are never rewritten, lossy doubles are surfaced as text with `numbers_as_text`, and `representation` flips between "source" and "source_records". It also explains that an empty `facts` is a meaningful negative result rather than an error — a genuinely useful disclosure.

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 core identification and the unfiltered baseline are front-loaded, and each sentence adds information rather than restating the name. The phrasing around non-representable numbers is noticeably tangled and could be tightened without loss.

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 an output schema present, the description need not enumerate return fields, and it covers inputs, filtering semantics, and the representation switch adequately. For a potentially very large whole-document fetch it gives no signal about payload size or response handling, which is the main remaining gap.

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

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

Schema coverage is 0%, so the description carries the load and does so substantively: `cik_or_ticker` accepts a CIK, exact ticker, or exact company name, and taxonomy/concept matching is literal and case-sensitive, with concept optional given taxonomy. What is missing is any sense of valid taxonomy identifiers (e.g. us-gaap) or concept formatting, which would prevent avoidable empty results.

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 resource: the SEC companyfacts document of one company, returned unchanged. It implies differentiation from get_companyconcept via the optional taxonomy/concept narrowing, but never names a sibling outright, so an agent must infer the boundary itself.

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 does explain the two modes (unfiltered vs. taxonomy/concept-filtered) and what each returns, which is genuine usage guidance. It never says when to prefer get_companyconcept or get_frames instead, nor any prerequisite (SEC user-agent / rate limits), leaving tool selection partly 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 description adds substantial behavioral context beyond the readOnlyHint and openWorldHint annotations: redirects are not followed, text may be null if bytes do not decode strictly as UTF-8, page boundaries can split characters, sha256 and total_bytes describe the whole file, and next_offset is null on the last page. It also warns that file contents are filer-authored material, not instructions, which is important open-world safety context.

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

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

The purpose is front-loaded in the first sentence, followed by dense but relevant usage and return-field details. Some clauses are packed together, but nearly every sentence contributes practical information for invoking or interpreting the tool.

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, open-world paginated file retrieval tool, the description covers URL formats, pagination, byte handling, checksum semantics, and content-type context. It is mostly complete, though the max_bytes parameter and any practical size limits remain unaddressed; the existing output schema reduces the need to explain return fields further.

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 0% schema description coverage, the description must carry parameter meaning. It fully explains url including accepted SEC URL forms and explains offset indirectly through the byte-range and next_offset pagination behavior, but it never explicitly defines max_bytes or its default/limit, leaving one of three parameters under-specified.

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

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

The description clearly states a specific action and resource: fetching any file from a filing folder or an SEC company list byte-for-byte, one page at a time. It is distinguishable from generic file tools, but it does not explicitly contrast itself with sibling tools such as get_filing_text, get_filing_xbrl, or get_filing_document listing tools.

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 through the accepted URL formats and pagination instructions, giving the agent a clear sense of when this tool applies. However, there is no explicit guidance on when to prefer this tool over alternatives like get_filing_text or get_filing_xbrl, nor any stated exclusions.

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, and the description adds real behavioral detail beyond them: pagination via `next_start`, a 40-match cap, case-insensitive matching, character (not byte) offsets, and a provenance rule requiring `original`/`transformation` to be quoted. It also warns that filer-authored text must never be treated as instructions, which is exactly the kind of 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 what the tool returns, then mode behavior, then the safety caveat — a sensible order. The opening sentence is a fragment and the provenance sentence is slightly dense, but no sentence is expendable.

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?

Although an output schema exists, the description still explains the shape of pagination state (`next_start` null-or-not) and match records, plus the provenance obligation for quoting. Nothing an agent needs to call this correctly and cite it responsibly 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 coverage is 0%, so the description carries the full burden and does: `url` (accepted extensions and where to obtain it), `find` (phrase semantics, case-insensitivity, 40-match limit, start-relative), `start` (character offset), and `max_chars` (characters returned from offset). All four parameters gain meaning not present in the bare 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 concrete verb and resource ("plain text extracted from a filing document") and immediately positions itself against the sibling that returns the raw file byte for byte (`get_filing_document`). An agent can distinguish the transformed view from the original 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 clear entry conditions: `url` comes from `list_filings` or an exhibit URL from `list_filing_documents`, and it spells out the two modes (paginated read vs `find` search). It implies rather than states when to prefer this over `get_filing_document` or `get_filing_xbrl`, so it stops short of explicit when-not guidance.

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?

Beyond the read-only annotation, the description discloses fallback filing selection, unresolved-file handling, warnings, duplicate fact preservation, no arc combination, paging behavior, and the fact that files are found only from what the filing publishes. These are substantive behavioral traits an agent needs before invoking the 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?

The description is long and dense, but it is front-loaded with the core purpose and then organized by selection logic, parts, concept filtering, and file discovery. The length is largely justified by the tool's complexity, though some sentences could be more scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a 10-parameter tool with complex XBRL part semantics, the description covers filing selection, part behavior, concept filtering, paging, unresolved candidates, and file discovery. Because an output schema exists, it does not need to explain return values, but its extra return-shape details are still coherent and helpful.

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 0% schema description coverage across 10 parameters, the description compensates extensively by defining `part` modes, `concepts` naming formats, paging via `offset`/`limit`, and the roles of `accession_number`, `form`, `as_of`, `instance_file`, and `schema_file`. It leaves `cik_or_ticker` implicit and does not state limit bounds or default behavior, so it is strong but not exhaustive.

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

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

The description states a specific resource, the XBRL files of one filing as the filer wrote them, and a specific access pattern, one `part` at a time. It is clearly distinct from document/text siblings, but it does not explicitly name or contrast those 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?

It gives detailed guidance on selecting the filing via `accession_number`, `form`, and `as_of`, and explains what each `part` returns. It does not explicitly state when not to use this tool or name alternative sibling tools for non-XBRL needs.

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 and openWorldHint, so safety is covered; the description adds genuinely new behavior: arguments are syntax-checked only and passed through as-is, an unpublished frame yields NOT_FOUND, and numbers a double cannot carry exactly come back as SEC-written text with `numbers_as_text` flagging them. That is real operational context beyond the 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?

Front-loaded with the purpose, then parameter semantics, then edge-case behavior — a sensible order with no filler. The backtick-heavy sentence fragments make it slightly choppy, but every sentence 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?

An output schema exists, so return values need no explanation, and the description still covers the notable output quirk (numbers_as_text) plus the NOT_FOUND case and pass-through validation. The only real gap is the absence of any guidance on `taxonomy` and `concept` values, which for a 0%-coverage schema is a meaningful omission.

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 parameter burden. It does a good job on `unit` (with concrete example values 'USD', 'shares', 'USD-per-shares', 'pure') and `period` (CY2023 / CY2023Q4 / CY2023Q4I), but says nothing about `taxonomy` or `concept`, leaving two of four required parameters undocumented anywhere.

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?

Opens with a specific verb+resource and a precise shape: 'one fact per company for one concept, unit and calendar period, as the SEC aggregates them.' That shape implicitly separates it from get_companyconcept (one company, many periods) and get_companyfacts (all facts for one company), so the agent can pick the right tool without opening schemas.

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 through the description of the data shape; the description never says when to prefer this over get_companyconcept or get_companyfacts, nor states any preconditions. The period/unit explanations give de facto invocation guidance, but no explicit when/when-not 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 readOnlyHint=true and openWorldHint=true, so safety is covered; the description goes further by disclosing that the payload is byte-faithful ('unchanged', names/tickers/addresses exactly as given) and that numeric precision is preserved by falling back to the SEC's original text, listed in `numbers_as_text`. It also describes the shape of `older_files`. The only notable gap is that it never says what happens on an invalid ticker or how large the recent table is.

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 identity and immutability guarantee is front-loaded in the first sentence, then return structure is layered on. It is dense but every clause carries information; only the line-wrapped formatting and the slightly buried `numbers_as_text` explanation cost it a point.

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 an output schema present, the description needn't detail return values, yet it usefully explains the nested `older_files` entries and the numeric-text fallback that a schema alone would not convey. For a two-parameter read tool it is close to complete; the missing pieces are error behavior and the identifier format for `cik_or_ticker`.

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

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

Schema description coverage is 0%, so the description must carry the parameters. It fully explains `include_older_files` (returns each file in `older_files` as {name, payload, numbers_as_text}, in listed order), but `cik_or_ticker` receives no treatment at all — no format, casing, or whether zero-padded CIKs are accepted, despite being the sole required 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 resource (the SEC submissions document for one company) and its key property (returned unchanged), which is enough to separate it from get_companyfacts / get_companyconcept that return derived data. It does not, however, name any sibling or explicitly contrast itself with list_filings, so the differentiation is inferential 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?

There is no explicit 'use this when...' routing versus lookup_company or list_filings, but the description does give one actionable condition: filings older than the recent table live in `filings.files`, and `include_older_files` fetches them. That is useful implied guidance for the parameter decision, though nothing tells the agent when to prefer this tool over list_filings for filing 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?

With readOnlyHint/openWorldHint already covering the safety profile, the description goes well beyond: it discloses that results are parsed from the page's HTML table by the rules in `transformation`, that unparseable links are omitted and surfaced in `skipped_rows` and `warnings`, and that the type label is SEC's own ('8-K', 'EX-99.1', 'GRAPHIC') without indicating filed vs furnished. Those are non-obvious caveats an agent needs before trusting the output.

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 return shape in the first sentence, then covers input, row fields, provenance, and caveats in a tight sequence. Every clause adds information; nothing 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?

Output schema exists, yet the description still names the per-row fields (sequence, description, type, size, document, url) and the auxiliary outputs (skipped_rows, warnings), and points at get_filing_document for the raw page. For a single-parameter read tool, nothing material 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 coverage is 0% — the single `url` property has no description at all — so the description has to carry it, and it does: 'any file URL of the filing' plus the note that such URLs come from list_filings or search_filings. It still doesn't clarify whether query strings/fragments or non-primary documents are accepted, keeping it off 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?

Names the exact resource — the rows of one filing's index page — and enumerates what those rows contain (main document, exhibits, data files). That distinguishes it cleanly from list_filings (the list of filings) and get_filing_document (raw page bytes), so an agent can pick it 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?

Gives a concrete entry condition by tying the url parameter to 'as returned by list_filings or search_filings', which tells the agent which sibling produces the input. It also implicitly separates this tool from get_filing_document by saying that tool returns the page byte for byte. No explicit exclusions or when-not-to-use statement, so not a 5.

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

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

Annotations only cover readOnlyHint and openWorldHint, and the description adds real behavioral context on top: ordering is never re-sorted or merged, an unreadable older file is an error rather than a short list, `warnings` names dropped rows, and `complete` reflects truncation or omissions. It stops short of permission, rate-limit, or pagination-cost detail, but the failure and truncation semantics are unusually well disclosed.

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 ordering constraint is front-loaded before filtering detail, and backticked identifiers make it scannable despite the dense run-on punctuation. Some sentences (the back-to-back semicolon clauses around `form`/`as_of`) could be split for readability, 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?

For a five-parameter tool with warnings, a `complete` flag, and dynamic SEC column keys, the description covers ordering, filtering, error behavior, and truncation well. The `record`/`url`/`source` expansion is partly redundant given an output schema exists, while the unexplained required `cik_or_ticker` is the remaining 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 0%, so the description carries the full load and does most of it: `form` is a literal comparison with None keeping everything, `include_amendments` also admits "<form>/A", `as_of` is YYYY-MM-DD with an on-or-before rule plus exclusion-to-warnings, and `limit` caps rows. The required `cik_or_ticker` parameter is never described at all, leaving the one mandatory input unstated.

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?

Opens with a concrete statement of what is returned: rows of a company's submissions filing tables, in the SEC's order. The resource and scope are unmistakable, but the definition never names or distinguishes itself from siblings such as search_filings or list_filing_documents, so an agent has no in-description routing signal.

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 through the filter semantics (form literal matching, include_amendments, as_of cutoff) rather than stated as when-to-use guidance, and no alternative tool is ever named. Absent any exclusions or comparison to search_filings, the agent must infer the choice 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 readOnlyHint and openWorldHint, but the description adds substantial behavior beyond them: strict equality matching with case and whitespace normalization rules, the three-valued resolution status, the fact that a company with several tickers yields several rows, and the feed's coverage limitation. Minor misstep is the dangling reference to "the response contract" for `numbers_as_text`, which an agent cannot resolve from this text alone.

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 core operation, and nearly every sentence carries genuine matching or status semantics. The enumeration of match fields (`cik`, `matched_on`, `record`, `numbers_as_text`) partly duplicates the output schema that already exists for this tool, and the mid-paragraph line breaks make it denser than 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?

With an output schema present, the description need not detail return values, yet it still explains the meaning of `status` and `matched_on` — the parts an agent must reason about. Combined with the coverage caveat about current tickers only, an agent has enough to call this correctly and interpret results.

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% — the single `query` string has no description at all — so the description must carry the load, and it does: it specifies that digits are matched against `cik_str`, and that ticker and title matching ignore case, with runs of spaces collapsed in titles. It stops short of stating precedence when a string could match more than one field, though the ambiguity status partially covers that outcome.

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 opening sentence states a specific verb and resource — find rows of the SEC's company_tickers.json — and defines the accepted key types (CIK, ticker, title). It implicitly separates this from the sibling tools, which consume a CIK rather than resolve one, and the closing note that a CIK not in the feed can still be passed to every other tool makes that relationship explicit.

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

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

Usage is well-framed: exact-match-only (no prefix/suffix/fuzzy), how to read each `status` value, and what to do on "ambiguous" (choose one and use its CIK). It also warns that the feed contains only current tickers and titles. What it lacks is an explicit statement of when to reach for this tool versus calling a sibling directly with a known CIK, though the closing sentence nearly says it.

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

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

Beyond the readOnly/openWorld annotations it discloses relevance ordering, pagination through next_offset, URL construction per CIK, the unresolved case for multi-CIK hits, numeric-as-text ambiguity, and a prompt-injection caveat about filer-supplied text. That is substantial added context; only rate limiting and how the index handles very broad queries are left out.

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 well with query semantics first, but much of the middle is spent explaining record/urls/numbers_as_text return structure that an existing output schema already conveys, making the passage longer than needed for invocation guidance.

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?

Covers query syntax, form and date filtering, ordering, pagination, and a safety caveat, which is nearly everything needed to call it correctly. It stops short of documenting limit and page-size behavior, so an agent must infer how next_offset relates to limit.

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 0% schema coverage the description carries the full burden and largely does: query syntax (all words, quoted phrases, OR), forms (comma-separated, amendments included, None = all), and filed_from/filed_to as inclusive YYYY-MM-DD. limit and offset are only partly addressed (offset via next_offset), leaving two of six params under-explained.

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 names a specific verb and resource ('find filings whose text contains given words') and pins the mechanism ('SEC's full-text search'), which clearly separates it from list_filings and get_filing_document among the siblings. An agent can pick it 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?

Usage is implied rather than stated: the text shows how to phrase a boolean query and warns to read the passage before relying on a hit, and it limits scope to filings since 2001. However, no sibling alternative is named (e.g. listing filings by company/date instead of searching text), and there are no explicit when-not conditions.

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