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

With no annotations, the description carries the full behavioral burden and does so well: it discloses ambiguity handling ("ambiguous names return candidates, never a guess"), partial coverage, staleness semantics, and that source is authoritative. Only the return payload shape is left unaddressed.

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 clause, followed by tightly packed caveats. It is dense but efficient; the telegraphic second half ("fresh != correct; source is authoritative") is informative though slightly oblique.

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

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

For a tool with no annotations and no output schema, the description should describe the returned caller representation, but it only says ambiguous names yield "candidates." Behavioral caveats are covered, yet the return contract is underspecified.

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% with three undocumented optional params, so the description must compensate. It partially does: it distinguishes claim_id as one lookup path from qualname+path as another and notes path is optional, but it gives no format, mutual-exclusivity, or precedence rules for the parameters.

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 ("List known callers") and names the two lookup keys (claim_id or qualname+path), so the agent knows exactly what it retrieves. It does not explicitly differentiate itself from nearby siblings like tmf_readers/tmf_writers, which would have pushed it to 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?

The description implies two valid invocation modes (by claim_id, or by qualname plus optional path), which is useful context for choosing inputs. However, it never states when this tool is preferred over tmf_readers, tmf_writers, or tmf_retrieve, so alternative selection 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?

With no annotations, the description carries the full burden and does substantial work: it discloses determinism, thinness of output, partial coverage, 'fresh != correct', source as authoritative, and graceful degradation of stale data to source. These are meaningful caveats beyond the schema, though it omits auth, rate limits, and any failure/error behavior.

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

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

Front-loads the purpose ('start here') and packs caveats efficiently into a few clauses with no filler. The telegraphic, semicolon-heavy style is slightly cryptic but every clause adds signal.

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 and no annotations exist, so the description must fully specify behavior. It covers return shape and caveats reasonably well, but leaves the two parameters undefined and gives no sense of size/scope limits despite a max_chars control, leaving notable gaps for a tool that is meant to be the first stop.

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% for both parameters, so the description must compensate, and it does not. It never explains the 'question' format/expectations nor what 'max_chars' (minimum 180) controls or how truncation affects the returned bundle.

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 clear verb and resource ('Return one deterministic thin context bundle with anchors and key fresh graph relations') and frames the tool as the entry point for codebase investigation. It distinguishes itself from the generic grep workflow, though the term 'context bundle' remains abstract and it does not name any sibling tool directly.

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?

'Investigating a codebase: start here; usually cheaper than grep plus whole-file reading' gives a positive recommendation and a comparison to a manual alternative. However it offers no explicit when-not conditions or routing to the many siblings (tmf_retrieve, tmf_fragment, tmf_explain), so usage is only implied.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It usefully states that coverage is partial, freshness does not equal correctness, the source is authoritative, and stale results should degrade to source, but it omits operational details such as side effects, permissions, or return format.

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 short and front-loaded, stating the core action before the flags and caveats. The semicolon-separated shorthand is efficient, though phrases like 'fresh != correct' are slightly cryptic.

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 two-parameter tool with no output schema, the description covers the main purpose, the 'full' flag, and data-quality caveats. However, it does not explain return values or when to prefer this tool over siblings, leaving gaps an agent might need to resolve.

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% for two parameters. The description adds meaning for 'full' by saying it includes thick body/source-bound details, and 'claim_id' is implicit from 'Explain one claim', but the identifier's format or constraints are not described.

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: 'Explain one claim', and adds what the 'full' mode includes. It clearly identifies the operation but does not differentiate itself from sibling tools such as tmf_retrieve or tmf_context. This meets the definition of a clear purpose without sibling differentiation.

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

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

The description gives no guidance on when to use this tool versus alternatives like tmf_retrieve or tmf_context. It only explains a parameter-level option ('full=true includes thick body/source-bound details') and offers data caveats, not usage conditions or 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?

With no annotations, the description carries the full burden and does so: it enumerates the return fields, states that missing/stale entries return no verified hops, that unsupported relations or invalid bounds raise an error, that it will not modify source or refresh derived claims, and warns 'fresh does not mean correct.'

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 front-loaded: purpose, entry source, return fields, recommended config, error behavior, and non-goals are ordered sensibly. Slightly verbose for a description, but every sentence carries distinct operational 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 7-parameter traversal tool with no output schema, the description compensates by naming the returned fields (verified_hops, boundaries, gaps, stale_or_unknown, stop_reason, coverage) and by covering error and staleness behavior, so an agent has what it needs to invoke 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 description coverage is 100%, so the schema already documents each parameter; the baseline is 3. The description adds value by prescribing which parameter values to start with and by clarifying entry semantics beyond the schema, earning a bump.

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: 'Explore indexed code relationships around a known claim before a cross-file change.' It explicitly contrasts with sibling and non-goal behavior ('This does not return a complete dependency graph'), letting an agent place it against tmf_callers/tmf_readers/tmf_subtypes.

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 preconditions ('Get entry from tmf_context or tmf_retrieve; it is a claim ID, not a path or symbol name'), recommended initial call shape (relations=["calls"], hop_limit=1, boundary_types=["function"], semantic_boundaries=false), and routes to alternatives (tmf_stale_slice for stale claims, tmf_explain(full=true) for full details).

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

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

With no annotations provided, the description carries the full burden and does reasonably well: it discloses partial coverage, that cache freshness does not imply correctness, that source is authoritative, and that stale results should degrade to source. It does not, however, cover pagination, permissions, or result size 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?

Extremely dense and front-loaded: one core sentence establishes the action and keys, and the trailing caveats about coverage and staleness each carry distinct, non-redundant information. No 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 read-only lookup tool with no output schema and no annotations, the description covers the important epistemic caveats (partial coverage, stale vs correct, ambiguous candidates) but never describes what a returned 'reader' entry looks like or how ambiguity is presented, leaving a gap an agent calling this blind would notice.

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

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

Schema description coverage is 0%, so the description must compensate for three undocumented parameters. It explains the role of each ('declaration claim_id or qualname plus optional path'), clarifying that path is optional and that claim_id/qualname are lookup keys, but adds no format, syntax, or mutual-exclusivity details.

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 ('List known readers') and names the lookup keys (declaration claim_id or qualname plus optional path). It is distinguishable from sibling tmf_writers by the resource, though it never explicitly contrasts with closely related siblings like tmf_callers or tmf_retrieve.

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 through 'ambiguous names return candidates' and 'stale should degrade to source', which effectively tells the agent to fall back to source when freshness is in doubt. However, it gives no explicit when-to-use/when-not guidance or naming of alternatives among the many sibling tools.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses accuracy caveats — 'partial coverage; fresh != correct; source is authoritative; stale should degrade to source' — which is real behavioral value, but nothing about result shape, cost of the limit, or pagination behavior is given.

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?

Very compact, front-loads the 'start here' guidance, and every clause carries information. The telegraphic phrasing ('fresh != correct', 'stale should degrade to source') is dense but readable, not 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 tool with no output schema, no annotations, and 0% schema coverage, the description covers accuracy/trust caveats well but leaves gaps: what a 'thin TMF claim' looks like in the response, and the meaning of the limit parameter are not addressed.

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 schema documents nothing. The description compensates partially by specifying the query is 'lexical' (a meaningful constraint not in the schema), but the `limit` parameter (1-50) is never explained or bounded in prose.

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: 'Retrieve thin TMF claims for a lexical query', and positions itself as the entry point for codebase investigation. It also distinguishes itself from grep as an alternative approach, though it doesn't differentiate from close siblings like tmf_fragment or tmf_context.

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?

'Investigating a codebase: start here' and 'usually cheaper than grep plus whole-file reading' give clear context for when to reach for this tool, plus a fallback rule ('stale should degrade to source'). It stops short of naming when a sibling such as tmf_fragment or tmf_context is preferable.

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

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

With no annotations, the description carries the full burden and does so: it enumerates return fields (claim_fresh, required_reads, retained_fresh_bindings, side_effect_checks, stop_rule), states error behavior for unknown IDs, and prominently discloses limits ('bounded heuristics, not proof of complete dependency coverage', 'fresh does not mean correct'). This is unusually rich behavioral 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?

Front-loaded with the purpose, then return fields, then usage constraints, so an agent gets the essentials in the first sentence. It is dense but most sentences earn their place; the unknown-claim-ID error is somewhat restated (once as 'do not invent IDs', once as 'an unknown claim ID raises an error'), which costs 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?

There is no output schema, so the description must carry the return contract, and it does — listing the exact returned fields plus the stop_rule and side-effect-check obligations. Combined with the error path and the freshness caveat, nothing an agent needs to invoke and 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%, so 3 is the baseline, but the description adds real guidance beyond the schema: claim_id must come from a prior tmf tool and must not be invented, and the task terms in 'question' influence source-reading selection. It does not add syntax detail for the two capped-integer parameters, which the schema already documents well.

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 precise verb and resource: 'Plan which current source to re-read after a stored claim becomes stale.' It names the sibling tools that produce the claim_id (tmf_context, tmf_retrieve, tmf_explain) and clearly scopes itself as read-planning only, distinguishing it from edit or index-refresh 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?

Gives an explicit trigger ('after a stored claim becomes stale, for example after a merge'), an explicit exclusion ('plans reads only: it does not perform edits, refresh the index, or guarantee freshness'), and routes the agent elsewhere on failure ('rediscover the target with tmf_retrieve'). When-to-use, when-not, and alternatives are all present.

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

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

With no annotations, the description carries the full burden and does disclose several non-obvious behavioral traits: partial coverage, freshness not equaling correctness, source authority, and degradation guidance for stale data. It still omits basic traits like read-only safety, side effects, and authentication requirements, but the provided caveats are valuable.

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 two short sentences with no wasted words, and the purpose is front-loaded. The second sentence is telegraphic and could be slightly clearer, but overall it is efficient and well-structured.

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

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

Given no annotations and no output schema, the description should explain what the status report returns and how to interpret it. It does not describe the output format, possible status values, or what 'claim', 'freshness', and 'cache status' concretely mean, leaving the agent under-informed for correct invocation.

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

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

The tool takes zero parameters, so there are no parameter semantics to clarify. Per the evaluation rule, a zero-parameter tool receives a baseline score of 4 for this dimension.

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 (Report) and resource (claim/freshness/cache status), making the tool's function identifiable. However, it does not differentiate from any of the many sibling tools such as tmf_stale_slice or tmf_retrieve, leaving ambiguity about scope.

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 guidance is provided on when to use this tool versus alternatives. The phrase 'stale should degrade to source' is an interpretation rule, not a condition for calling the tool, and no context or exclusions are 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?

With no annotations, the description carries the full burden, and it does disclose meaningful traits: partial coverage, freshness not equating to correctness, source being authoritative, and degraded behavior when stale. However, it never states the return shape, whether results are ordered/limited, or what 'degrade to source' means operationally, and the phrasing is jargon-dense.

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

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

Two compact sentences with the main action and lookup keys front-loaded. The semicolon chain packs caveats efficiently, though the telegraphic style reduces readability slightly.

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 graph-query tool with no output schema and no annotations, the description should clarify result structure, edge semantics, and ordering/limits. It covers coverage and freshness caveats but leaves the return shape and edge meaning to inference, so it is only partially complete.

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

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

Schema description coverage is 0%, so the description must compensate: it does name all three parameters (claim_id, qualname, path), flags path as optional, and explains that ambiguous qualnames yield candidate matches. It still doesn't define the difference between claim_id and qualname or when each is preferred, so the compensation is partial.

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 verb+resource is specific: 'List known Java subtype/implementor edges' with the lookup keys (claim_id or qualname). It distinguishes itself from siblings like tmf_callers/tmf_readers by naming the edge kind, though it never explicitly contrasts the 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 hints that ambiguous names return candidates and that stale data should degrade to source, but gives no explicit when-to-use guidance or named alternatives among the ten sibling tools. An agent must infer selection from the key 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?

With no annotations, the description carries the full burden and does real work: it declares the operation read-only, notes that the optional path is containment-checked (a security/validation property), and discloses that coverage is partial and that stale data should degrade to the authoritative source. It stops short of describing failure modes or return format, but the safety and correctness caveats are substantive.

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 definition is a single front-loaded clause stating what the tool does, followed by terse caveats. The telegraphic semicolon style is dense but every clause carries distinct information, so little space 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?

With no annotations, no output schema, and no parameter descriptions, the description should carry more weight than it does. It conveys behavior and correctness caveats well, but omits what the tool returns and how it relates to sibling tools like tmf_stale_slice, which an agent would need 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 0%, so the description must compensate for the single 'path' parameter. It does add two useful facts – the path is optional and is containment-checked – but gives no format, syntax, or example, leaving the agent to infer what a valid path looks like.

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 phrase 'Read-only source derivation into .tmf cache' identifies a verb-like action (deriving/warming) and a resource (.tmf cache), so the agent gets a rough sense of what happens. However, the phrasing is jargon-heavy and it never distinguishes itself from siblings like tmf_retrieve, tmf_stale_slice, or tmf_fragment, leaving the exact scope of 'warm' ambiguous.

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 statement of when to call this versus the nine sibling tools. The caveats ('Partial coverage; fresh != correct; source is authoritative; stale should degrade to source') hint at trust and fallback behavior but never tell the agent which situations should route here.

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

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

With no annotations, the description carries the full burden, and it does disclose non-obvious traits: ambiguity returns candidates and results are partial/degradable. However, the phrases 'fresh != correct' and 'stale should degrade to source' are cryptic and leave the actual retrieval/fallback behavior underspecified.

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?

Compact and front-loaded, with the core action leading. But the terse telegraphic fragments ('fresh != correct', 'stale should degrade to source') trade clarity for brevity, weakening the structure of an otherwise short definition.

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 3-param, no-annotation, no-output-schema read tool, the description covers lookup semantics and data-quality caveats but does not describe the return shape beyond 'candidates' or the fallback workflow it alludes to. Adequate but with clear gaps.

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

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

Schema description coverage is 0%, so the description must compensate, and it does name all three keys (claim_id, qualname, path) and flags path as optional. It gives no format or precedence rules (e.g., what happens if both claim_id and qualname are supplied), so the mapping is only partially meaningful.

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 ('List known writers') and identifies the lookup keys (claim_id/qualname, optional path), which distinguishes it from tmf_readers and tmf_callers. It does not explicitly name the sibling it differs from, so the contrast is inferable 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?

No explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The 'ambiguous names return candidates' clause hints at behavior but is not routing guidance, and the quality caveats ('source is authoritative') are data warnings, not usage conditions.

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